🏆
Ranglisten
LLM Leaderboard
Reale Messergebnisse aller getesteten Sprachmodelle auf echter, benannter Hardware – bewertet nach roher Geschwindigkeit (Performance in Token pro Sekunde, Prefill und Zeit bis zum ersten Token) und nach praktischer Aufgaben-Qualität in vollständigen Agenten- und Chat-Abläufen (Harness). Wähle unten einen Benchmark-Typ oder filtere nach Modell, Hersteller und Hardware, um genau zu sehen, was jeweils geprüft wird und wie die Ergebnisse zustande kommen.
⚡ Performance (tok/s)🤖 Harness-Qualität👥 Concurrency🖥️ echte Hardware
| # | Modell / Hersteller | Messwerte | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 141,98 tok/s TG Prefill 4.212 · TTFT 12.237 ms | 10× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 2 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 124,89 tok/s TG Prefill 2.476 · TTFT 6.821 ms | 5× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 3 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 64,50 tok/s TG Prefill 1.366 · TTFT 1.420 ms | 1× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 4 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 146,86 tok/s TG Prefill 2.806 · TTFT 12.191 ms | 10× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliQ4_0 | Details → | |
| 5 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 121,80 tok/s TG Prefill 1.943 · TTFT 7.408 ms | 5× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliQ4_0 | Details → | |
| 6 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 66,20 tok/s TG Prefill 1.300 · TTFT 1.660 ms | 1× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliQ4_0 | Details → | |
| 7 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 106,99 tok/s TG Prefill 5.833 · TTFT 17.334 ms | 10× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 8 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 71,97 tok/s TG Prefill 3.029 · TTFT 9.456 ms | 5× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 9 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 63,15 tok/s TG Prefill 1.472 · TTFT 1.659 ms | 1× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 10 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 200,47 tok/s TG Prefill 5.303 · TTFT 7.750 ms | 10× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliMXFP4 | Details → | |
| 11 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 119,73 tok/s TG Prefill 3.482 · TTFT 4.698 ms | 5× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliMXFP4 | Details → | |
| 12 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 64,41 tok/s TG Prefill 2.523 · TTFT 858 ms | 1× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliMXFP4 | Details → | |
| 13 | gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 111,85 tok/s TG Prefill 2.041 · TTFT 17.689 ms | 10× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliMXFP4 | Details → | |
| 14 | gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 79,06 tok/s TG Prefill 1.478 · TTFT 11.284 ms | 5× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliMXFP4 | Details → | |
| 15 | gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 48,95 tok/s TG Prefill 919 · TTFT 2.243 ms | 1× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliMXFP4 | Details → | |
| 16 | gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 135,08 tok/s TG Prefill 1.548 · TTFT 12.948 ms | 10× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 17 | gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 100,67 tok/s TG Prefill 1.446 · TTFT 6.855 ms | 5× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 18 | gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,23 tok/s TG Prefill 1.354 · TTFT 1.459 ms | 1× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 19 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 136,58 tok/s TG Prefill 2.934 · TTFT 8.734 ms | 10× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 20 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 116,18 tok/s TG Prefill 2.075 · TTFT 5.320 ms | 5× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 21 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 81,10 tok/s TG Prefill 1.729 · TTFT 1.247 ms | 1× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 22 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 169,42 tok/s TG Prefill 2.873 · TTFT 7.817 ms | 10× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 23 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 138,96 tok/s TG Prefill 2.158 · TTFT 4.629 ms | 5× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 24 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 76,77 tok/s TG Prefill 1.830 · TTFT 1.055 ms | 1× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 25 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 161,05 tok/s TG Prefill 5.256 · TTFT 6.170 ms | 10× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 26 | gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 51,11 tok/s TG Prefill 899 · TTFT 2.279 ms | 1× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliMXFP4 | Details → | |
| 27 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 129,46 tok/s TG Prefill 3.442 · TTFT 3.808 ms | 5× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 28 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 81,15 tok/s TG Prefill 2.472 · TTFT 986 ms | 1× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 29 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 233,28 tok/s TG Prefill 4.282 · TTFT 4.702 ms | 10× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 156,02 tok/s TG Prefill 3.859 · TTFT 2.570 ms | 5× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 31 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 85,78 tok/s TG Prefill 3.326 · TTFT 594 ms | 1× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 32 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 67,87 tok/s TG Prefill 1.288 · TTFT 1.499 ms | 1× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 33 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 72,08 tok/s TG Prefill 1.293 · TTFT 1.669 ms | 1× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliQ4_0 | Details → | |
| 34 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 75,08 tok/s TG Prefill 1.575 · TTFT 1.551 ms | 1× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 35 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 70,74 tok/s TG Prefill 2.529 · TTFT 846 ms | 1× | NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAM | llama.cppopenclaw_cliMXFP4 | Details → | |
| 36 | gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 18,07 tok/s TG Prefill 96 · TTFT 20.531 ms | 1× | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 37 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 139,97 tok/s TG Prefill 1.744 · TTFT 14.686 ms | 10× | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 38 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 119,24 tok/s TG Prefill 1.181 · TTFT 9.551 ms | 5× | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 39 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 101,04 tok/s TG Prefill 1.039 · TTFT 2.074 ms | 1× | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 40 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 341,53 tok/s TG Prefill 4.662 · TTFT 4.820 ms | 10× | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 41 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 299,90 tok/s TG Prefill 3.515 · TTFT 2.858 ms | 5× | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 42 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 172,41 tok/s TG Prefill 2.763 · TTFT 700 ms | 1× | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 43 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 371,66 tok/s TG Prefill 8.745 · TTFT 3.710 ms | 10× | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 44 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 303,07 tok/s TG Prefill 6.279 · TTFT 2.200 ms | 5× | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 45 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 189,23 tok/s TG Prefill 3.806 · TTFT 640 ms | 1× | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 46 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 448,17 tok/s TG Prefill 5.809 · TTFT 3.494 ms | 10× | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 47 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 361,70 tok/s TG Prefill 4.756 · TTFT 2.076 ms | 5× | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 48 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 211,09 tok/s TG Prefill 4.232 · TTFT 467 ms | 1× | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 49 | Codestral-22B-v0.122BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 623,04 tok/s TG Prefill 6.697 · TTFT 15.390 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 50 | Devstral-Small-250724BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 646,94 tok/s TG Prefill 10.489 · TTFT 10.971 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 51 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 575,74 tok/s TG Prefill 4.496 · TTFT 3.743 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 52 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 902,14 tok/s TG Prefill 9.553 · TTFT 2.416 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 53 | gemma-4-E4B-it8BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 902,59 tok/s TG Prefill 12.381 · TTFT 1.885 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 54 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 900,71 tok/s TG Prefill 9.991 · TTFT 2.386 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 55 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 899,11 tok/s TG Prefill 13.942 · TTFT 2.150 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 56 | Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 985,75 tok/s TG Prefill 7.733 · TTFT 2.448 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 57 | Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 997,65 tok/s TG Prefill 7.725 · TTFT 2.444 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 58 | NVIDIA-Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.005,67 tok/s TG Prefill 7.555 · TTFT 2.444 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 59 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.055,44 tok/s TG Prefill 10.341 · TTFT 9.706 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 60 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 944,04 tok/s TG Prefill 13.438 · TTFT 2.113 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 61 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.103,42 tok/s TG Prefill 5.051 · TTFT 11.207 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 62 | NVIDIA-Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.154,42 tok/s TG Prefill 8.806 · TTFT 2.065 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 63 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.348,35 tok/s TG Prefill 18.078 · TTFT 1.302 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 64 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.105,79 tok/s TG Prefill 14.121 · TTFT 1.691 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 65 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 799,04 tok/s TG Prefill 7.237 · TTFT 2.650 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 66 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.439,36 tok/s TG Prefill 8.063 · TTFT 7.868 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 67 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 818,85 tok/s TG Prefill 7.089 · TTFT 2.658 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 68 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.499,44 tok/s TG Prefill 8.022 · TTFT 7.851 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 69 | Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 814,30 tok/s TG Prefill 6.898 · TTFT 2.629 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 70 | Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.476,12 tok/s TG Prefill 7.819 · TTFT 7.689 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 71 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 869,38 tok/s TG Prefill 11.044 · TTFT 2.242 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 72 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.528,71 tok/s TG Prefill 17.513 · TTFT 6.225 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 73 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 803,48 tok/s TG Prefill 9.780 · TTFT 2.187 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 74 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 861,55 tok/s TG Prefill 6.134 · TTFT 2.760 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 75 | Ornith-1.0-35B35BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 890,62 tok/s TG Prefill 6.480 · TTFT 2.651 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 76 | North-Mini-Code-1.030.5BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 859,15 tok/s TG Prefill 7.281 · TTFT 2.530 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 77 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 888,96 tok/s TG Prefill 12.945 · TTFT 2.202 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 78 | Laguna-XS-2.133.4BPoolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 959,22 tok/s TG Prefill 7.286 · TTFT 2.879 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 79 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.525,69 tok/s TG Prefill 10.623 · TTFT 6.806 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 80 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.604,55 tok/s TG Prefill 6.804 · TTFT 8.073 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 81 | Ornith-1.0-35B35BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.586,19 tok/s TG Prefill 7.391 · TTFT 7.492 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 82 | North-Mini-Code-1.030.5BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.573,04 tok/s TG Prefill 8.004 · TTFT 7.551 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 83 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.617,88 tok/s TG Prefill 13.894 · TTFT 6.893 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 84 | Laguna-XS-2.133.4BPoolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.706,21 tok/s TG Prefill 8.777 · TTFT 7.343 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 85 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.623,26 tok/s TG Prefill 10.509 · TTFT 7.259 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 86 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.653,11 tok/s TG Prefill 13.572 · TTFT 6.808 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 87 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.623,15 tok/s TG Prefill 10.707 · TTFT 7.140 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 88 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.645,78 tok/s TG Prefill 14.123 · TTFT 6.609 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 89 | gemma-4-E4B-it8BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.755,52 tok/s TG Prefill 13.910 · TTFT 5.964 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 90 | Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.784,65 tok/s TG Prefill 8.304 · TTFT 6.952 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 91 | NVIDIA-Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.775,62 tok/s TG Prefill 8.642 · TTFT 6.861 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 92 | Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.774,36 tok/s TG Prefill 7.850 · TTFT 6.996 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 93 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.981,08 tok/s TG Prefill 15.983 · TTFT 5.309 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 94 | NVIDIA-Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 2.144,30 tok/s TG Prefill 10.533 · TTFT 5.598 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 95 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 2.412,27 tok/s TG Prefill 19.677 · TTFT 4.107 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 96 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 79,19 tok/s TG Prefill 670 · TTFT 33.965 ms | 10× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 126 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 97 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 73,30 tok/s TG Prefill 487 · TTFT 20.813 ms | 5× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 126 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 98 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 38,84 tok/s TG Prefill 258 · TTFT 10.963 ms | 1× | 2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 126 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 99 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,87 tok/s TG Prefill 1.120 · TTFT 20.453 ms | 10× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawIQ3_XXS | Details → | |
| 100 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 66,02 tok/s TG Prefill 838 · TTFT 12.155 ms | 5× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawIQ3_XXS | Details → | |
| 101 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 36,38 tok/s TG Prefill 714 · TTFT 2.760 ms | 1× | NVIDIA DGX SPARK (GB10) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawIQ3_XXS | Details → | |
| 102 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.555,31 tok/s TG Prefill 2.655 · TTFT 34.751 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 103 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 804,23 tok/s TG Prefill 2.435 · TTFT 15.796 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 104 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 164,58 tok/s TG Prefill 1.951 · TTFT 1.010 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 105 | NVIDIA-Nemotron-3-Super-120B-A12B120BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,01 tok/s TG Prefill 93 · TTFT 268.279 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 106 | NVIDIA-Nemotron-3-Super-120B-A12B120BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,03 tok/s TG Prefill 58 · TTFT 186.063 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 107 | NVIDIA-Nemotron-3-Super-120B-A12B120BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,11 tok/s TG Prefill 50 · TTFT 45.015 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 108 | Mistral-Medium-3.5-128B128BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,80 tok/s TG Prefill 136 · TTFT 225.066 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 109 | Mistral-Medium-3.5-128B128BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,46 tok/s TG Prefill 96 · TTFT 123.967 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 110 | Mistral-Medium-3.5-128B128BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,75 tok/s TG Prefill 72 · TTFT 29.692 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 111 | Devstral-2-123B-Instruct-2512123BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,14 tok/s TG Prefill 145 · TTFT 210.728 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 112 | Devstral-2-123B-Instruct-2512123BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,70 tok/s TG Prefill 124 · TTFT 113.211 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 113 | Devstral-2-123B-Instruct-2512123BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,78 tok/s TG Prefill 70 · TTFT 30.322 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 114 | GLM-4.5-Air106BZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,12 tok/s TG Prefill 94 · TTFT 251.044 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 115 | GLM-4.5-Air106BZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,55 tok/s TG Prefill 77 · TTFT 144.723 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 116 | GLM-4.5-Air106BZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,91 tok/s TG Prefill 73 · TTFT 29.342 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 117 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,20 tok/s TG Prefill 64 · TTFT 348.520 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 118 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,05 tok/s TG Prefill 71 · TTFT 151.213 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 119 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,25 tok/s TG Prefill 105 · TTFT 25.936 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 120 | gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 16,34 tok/s TG Prefill 115 · TTFT 189.253 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 121 | gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 11,17 tok/s TG Prefill 102 · TTFT 100.889 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 122 | gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,77 tok/s TG Prefill 84 · TTFT 23.842 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 123 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 10,41 tok/s TG Prefill 137 · TTFT 182.122 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 124 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 14,86 tok/s TG Prefill 112 · TTFT 113.417 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 125 | Ling-3.0-flash127.5BinclusionAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 10,50 tok/s TG Prefill 78 · TTFT 32.702 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 126 | MiniMax-M2.5230BMiniMax PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,11 tok/s TG Prefill 49 · TTFT 354.928 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 127 | MiniMax-M2.5230BMiniMax PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,68 tok/s TG Prefill 78 · TTFT 183.797 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 128 | MiniMax-M2.5230BMiniMax PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,96 tok/s TG Prefill 39 · TTFT 59.562 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 129 | Qwen3-Coder-Next79.7BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 197,72 tok/s TG Prefill 3.028 · TTFT 9.922 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 130 | Qwen3-Coder-Next79.7BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 111,86 tok/s TG Prefill 2.599 · TTFT 5.054 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 131 | Qwen3-Coder-Next79.7BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 52,73 tok/s TG Prefill 1.822 · TTFT 1.335 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 132 | Llama-3_3-Nemotron-Super-49B-v1_549BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 108,28 tok/s TG Prefill 1.036 · TTFT 25.801 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 133 | Llama-3_3-Nemotron-Super-49B-v1_549BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 66,29 tok/s TG Prefill 806 · TTFT 15.256 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 134 | Llama-3_3-Nemotron-Super-49B-v1_549BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 26,15 tok/s TG Prefill 752 · TTFT 3.251 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 135 | Nemotron-H-47B-Reasoning-128K47BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 65,50 tok/s TG Prefill 90 · TTFT 241.475 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 136 | Nemotron-H-47B-Reasoning-128K47BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,97 tok/s TG Prefill 120 · TTFT 105.288 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 137 | Nemotron-H-47B-Reasoning-128K47BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 24,61 tok/s TG Prefill 266 · TTFT 8.049 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 138 | Qwen3.5-122B-A10B122BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 11,84 tok/s TG Prefill 116 · TTFT 208.539 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 139 | Qwen3.5-122B-A10B122BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,79 tok/s TG Prefill 91 · TTFT 119.749 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 140 | Qwen3.5-122B-A10B122BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,05 tok/s TG Prefill 58 · TTFT 34.417 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 141 | Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 184,38 tok/s TG Prefill 3.855 · TTFT 5.993 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 142 | Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 136,39 tok/s TG Prefill 3.136 · TTFT 3.281 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 143 | Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 63,59 tok/s TG Prefill 1.700 · TTFT 1.520 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 144 | Seed-OSS-36B-Instruct36BByteDance Seed PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 117,48 tok/s TG Prefill 1.715 · TTFT 15.024 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 145 | Seed-OSS-36B-Instruct36BByteDance Seed PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 71,06 tok/s TG Prefill 1.341 · TTFT 8.487 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 146 | Seed-OSS-36B-Instruct36BByteDance Seed PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 29,99 tok/s TG Prefill 1.032 · TTFT 2.135 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 147 | NVIDIA-Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,91 tok/s TG Prefill 3.719 · TTFT 6.905 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 148 | NVIDIA-Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 185,17 tok/s TG Prefill 2.486 · TTFT 4.503 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 149 | NVIDIA-Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 82,38 tok/s TG Prefill 2.297 · TTFT 936 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 150 | Laguna-XS-2.133.4BPoolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 212,42 tok/s TG Prefill 4.204 · TTFT 7.880 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 151 | Laguna-XS-2.133.4BPoolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 151,93 tok/s TG Prefill 3.571 · TTFT 4.182 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 152 | Laguna-XS-2.133.4BPoolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 70,08 tok/s TG Prefill 2.192 · TTFT 1.273 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 153 | OpenReasoning-Nemotron-32B32BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 124,63 tok/s TG Prefill 2.910 · TTFT 13.342 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 154 | OpenReasoning-Nemotron-32B32BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 77,55 tok/s TG Prefill 2.327 · TTFT 6.323 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 155 | OpenReasoning-Nemotron-32B32BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 31,72 tok/s TG Prefill 1.260 · TTFT 1.939 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 156 | gemma-4-31B-it31BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 108,03 tok/s TG Prefill 121 · TTFT 163.657 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 157 | gemma-4-31B-it31BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,73 tok/s TG Prefill 574 · TTFT 19.191 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 158 | gemma-4-31B-it31BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 28,24 tok/s TG Prefill 502 · TTFT 3.937 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 159 | North-Mini-Code-1.030.5BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 208,75 tok/s TG Prefill 3.396 · TTFT 6.675 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 160 | North-Mini-Code-1.030.5BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 127,13 tok/s TG Prefill 2.805 · TTFT 3.716 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 161 | North-Mini-Code-1.030.5BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 72,90 tok/s TG Prefill 1.845 · TTFT 1.075 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 162 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 221,62 tok/s TG Prefill 6.455 · TTFT 4.958 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 163 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 150,92 tok/s TG Prefill 4.439 · TTFT 3.079 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 164 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 72,22 tok/s TG Prefill 2.606 · TTFT 941 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 165 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 223,26 tok/s TG Prefill 5.840 · TTFT 4.476 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 166 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 151,56 tok/s TG Prefill 5.059 · TTFT 2.775 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 167 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,17 tok/s TG Prefill 2.699 · TTFT 904 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 168 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 218,45 tok/s TG Prefill 4.085 · TTFT 7.280 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 169 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 158,98 tok/s TG Prefill 4.810 · TTFT 2.927 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 170 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 77,04 tok/s TG Prefill 2.750 · TTFT 887 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 171 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 234,08 tok/s TG Prefill 7.116 · TTFT 4.629 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 172 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 157,44 tok/s TG Prefill 5.388 · TTFT 2.798 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 173 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 79,32 tok/s TG Prefill 2.854 · TTFT 854 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 174 | Qwen3.6-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 95,64 tok/s TG Prefill 1.344 · TTFT 17.133 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 175 | Qwen3.6-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 76,06 tok/s TG Prefill 1.170 · TTFT 8.755 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 176 | Qwen3.6-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,15 tok/s TG Prefill 941 · TTFT 2.049 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 177 | Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 76,68 tok/s TG Prefill 2.234 · TTFT 966 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 178 | Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 162,67 tok/s TG Prefill 4.605 · TTFT 6.779 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 179 | Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 104,62 tok/s TG Prefill 3.528 · TTFT 3.829 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 180 | Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 41,51 tok/s TG Prefill 1.815 · TTFT 1.180 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 181 | Devstral-Small-250724BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 161,82 tok/s TG Prefill 5.708 · TTFT 7.791 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 182 | Devstral-Small-250724BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 126,19 tok/s TG Prefill 4.087 · TTFT 4.824 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 183 | Devstral-Small-250724BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 45,56 tok/s TG Prefill 2.801 · TTFT 1.230 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 184 | Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 170,04 tok/s TG Prefill 3.644 · TTFT 7.723 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 185 | Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 111,39 tok/s TG Prefill 2.569 · TTFT 4.744 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 186 | Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 45,30 tok/s TG Prefill 1.770 · TTFT 1.272 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 187 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 170,07 tok/s TG Prefill 4.885 · TTFT 6.913 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 188 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 108,92 tok/s TG Prefill 3.632 · TTFT 3.888 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 189 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 45,80 tok/s TG Prefill 1.823 · TTFT 1.259 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 190 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 177,00 tok/s TG Prefill 3.900 · TTFT 5.890 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 191 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 114,65 tok/s TG Prefill 3.192 · TTFT 3.231 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 192 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 60,67 tok/s TG Prefill 2.170 · TTFT 889 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 193 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 247,27 tok/s TG Prefill 5.437 · TTFT 3.732 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 194 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 192,70 tok/s TG Prefill 4.519 · TTFT 2.188 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 195 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 99,67 tok/s TG Prefill 3.153 · TTFT 626 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 196 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 185,72 tok/s TG Prefill 2.040 · TTFT 10.071 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 197 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 124,06 tok/s TG Prefill 1.850 · TTFT 5.352 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 198 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 54,00 tok/s TG Prefill 1.803 · TTFT 1.097 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 199 | Codestral-22B-v0.122BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 154,06 tok/s TG Prefill 4.443 · TTFT 9.034 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 200 | Codestral-22B-v0.122BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 102,38 tok/s TG Prefill 3.496 · TTFT 4.754 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 201 | Codestral-22B-v0.122BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 40,39 tok/s TG Prefill 1.837 · TTFT 1.479 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 202 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 204,85 tok/s TG Prefill 5.517 · TTFT 5.147 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 203 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 134,94 tok/s TG Prefill 4.042 · TTFT 3.043 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 204 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 54,41 tok/s TG Prefill 2.690 · TTFT 841 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 205 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 181,73 tok/s TG Prefill 3.947 · TTFT 5.816 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 206 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 117,49 tok/s TG Prefill 3.235 · TTFT 3.141 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 207 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 61,80 tok/s TG Prefill 2.428 · TTFT 795 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 208 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 179,37 tok/s TG Prefill 755 · TTFT 26.574 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 209 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 112,91 tok/s TG Prefill 1.213 · TTFT 8.186 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 210 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 51,06 tok/s TG Prefill 1.138 · TTFT 1.779 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 211 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 218,13 tok/s TG Prefill 4.747 · TTFT 5.848 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 212 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 126,81 tok/s TG Prefill 3.529 · TTFT 3.536 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 213 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 72,45 tok/s TG Prefill 2.419 · TTFT 1.011 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 214 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 207,49 tok/s TG Prefill 4.026 · TTFT 5.675 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 215 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 150,76 tok/s TG Prefill 3.259 · TTFT 3.120 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 216 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 72,52 tok/s TG Prefill 2.213 · TTFT 887 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 217 | gemma-3n-E4B-it8BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 220,77 tok/s TG Prefill 3.758 · TTFT 6.047 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 218 | gemma-3n-E4B-it8BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 116,57 tok/s TG Prefill 2.698 · TTFT 3.741 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 219 | gemma-3n-E4B-it8BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 48,95 tok/s TG Prefill 2.226 · TTFT 887 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 220 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 68,34 tok/s TG Prefill 3.961 · TTFT 5.236 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 221 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 59,43 tok/s TG Prefill 4.164 · TTFT 2.404 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 222 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,29 tok/s TG Prefill 3.392 · TTFT 610 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 223 | SmolLM2-1.7B-Instruct1.7BHuggingFaceTB PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,10 tok/s TG Prefill 45 · TTFT 281.637 ms | 5× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 224 | SmolLM2-1.7B-Instruct1.7BHuggingFaceTB PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,89 tok/s TG Prefill 38 · TTFT 81.741 ms | 1× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 225 | gemma-2-2b-it2BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,94 tok/s TG Prefill 52 · TTFT 404.593 ms | 10× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 226 | gemma-2-2b-it2BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,49 tok/s TG Prefill 35 · TTFT 283.919 ms | 5× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 227 | gemma-2-2b-it2BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,76 tok/s TG Prefill 31 · TTFT 59.057 ms | 1× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 228 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,02 tok/s TG Prefill 7 · TTFT 453.619 ms | 5× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 229 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,19 tok/s TG Prefill 9 · TTFT 227.569 ms | 1× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 230 | Llama-3.2-3B-Instruct3BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,09 tok/s TG Prefill 31 · TTFT 347.304 ms | 10× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 231 | Llama-3.2-3B-Instruct3BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,46 tok/s TG Prefill 35 · TTFT 360.878 ms | 5× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 232 | Llama-3.2-3B-Instruct3BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,99 tok/s TG Prefill 22 · TTFT 104.643 ms | 1× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 233 | Llama-3.2-1B-Instruct1BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 13,17 tok/s TG Prefill 122 · TTFT 228.054 ms | 10× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 234 | Llama-3.2-1B-Instruct1BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,93 tok/s TG Prefill 95 · TTFT 136.105 ms | 5× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 235 | Llama-3.2-1B-Instruct1BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,33 tok/s TG Prefill 65 · TTFT 38.290 ms | 1× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 236 | Qwen2.5-3B-Instruct3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,07 tok/s TG Prefill 33 · TTFT 360.019 ms | 10× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 237 | Qwen2.5-3B-Instruct3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,47 tok/s TG Prefill 33 · TTFT 369.084 ms | 5× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 238 | Qwen2.5-3B-Instruct3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,22 tok/s TG Prefill 24 · TTFT 103.262 ms | 1× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 239 | Qwen2.5-1.5B-Instruct1.5BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,11 tok/s TG Prefill 91 · TTFT 301.409 ms | 10× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 240 | Qwen2.5-1.5B-Instruct1.5BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,14 tok/s TG Prefill 67 · TTFT 194.902 ms | 5× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 241 | Qwen2.5-1.5B-Instruct1.5BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,93 tok/s TG Prefill 47 · TTFT 52.732 ms | 1× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 242 | Qwen2.5-0.5B-Instruct0.5BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 19,33 tok/s TG Prefill 171 · TTFT 178.576 ms | 10× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 243 | Qwen2.5-0.5B-Instruct0.5BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 19,64 tok/s TG Prefill 135 · TTFT 103.828 ms | 5× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 244 | Qwen2.5-0.5B-Instruct0.5BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 11,74 tok/s TG Prefill 85 · TTFT 29.146 ms | 1× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 245 | Qwen3-8B8.2BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,62 tok/s TG Prefill 9 · TTFT 232.748 ms | 1× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 246 | Qwen3-4B4BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,01 tok/s TG Prefill 6 · TTFT 506.953 ms | 5× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 247 | Qwen3-4B4BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,91 tok/s TG Prefill 15 · TTFT 142.282 ms | 1× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 248 | Mistral-Small-24B-Instruct-250123.6BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 153,12 tok/s TG Prefill 4.348 · TTFT 7.017 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 249 | Mistral-Small-24B-Instruct-250123.6BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 86,87 tok/s TG Prefill 3.428 · TTFT 3.916 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 250 | Qwen3-1.7B1.7BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,04 tok/s TG Prefill 48 · TTFT 383.019 ms | 10× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → |

