Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Anmelden Registrieren
Beta
🎮
Grafikkarte

Keine GPU (CPU-only)

Other
43Benchmarks
18Modelle
43Performance
0Harness
Beste Generation
70,9 tok/s
gpt-oss-20b
∅ Generation
8,3 tok/s
Schnitt aus 43 Läufen
Bester Prefill
218 tok/s
Prompt-Verarbeitung
Bester TTFT
569 ms
Time to First Token
Beste Harness-Quote
–%
noch kein Harness
🏆
gpt-oss-20b läuft am schnellsten auf dieser GPU · 70,9 tok/s
Bester Prefill: 218 tok/s · 18 Modelle getestet

Top-Modelle

Bester gemessener Durchsatz je Modell auf Keine GPU (CPU-only) – umschaltbar nach Generation, Prefill oder Kombiwert.

gpt-oss-20b20B
70,9 tok/s
Qwen3-30B-A3B-Instruct-250730B
26,0 tok/s
Qwen3-30B-A3B-Thinking-250730B
8,5 tok/s
Nemotron-3-Nano-4B4B
8,0 tok/s
Qwen3-Coder-30B-A3B-Instruct30B
6,7 tok/s
Nemotron-3-Nano-30B-A3B30B
6,6 tok/s
Nemotron-Cascade-2-30B-A3B30B
5,9 tok/s
gpt-oss-120b120B
5,3 tok/s
North-Mini-Code-1.0
5,1 tok/s
Qwen3.6-35B-A3B35B
4,3 tok/s
Anzeige
Performanceprofil

Durchsatz auf Keine GPU (CPU-only)

Jede Blase steht für ein Modell, eine Engine bzw. eine CPU – Position: Prompt-Verarbeitung (X) × Ausgabe (Y), Blasengröße: Anzahl Messläufe.

MODnach Modell

91,969,046,023,00,0055111166Prefill (tok/s)Generation (tok/s)gpt-oss-20b - 70,9 tok/s Generation, 119 tok/s Prefill, TTFT 95.764 ms (6 Laufe)gpt-oss-20bQwen3-30B-A3B-Instruct-2507 - 26,0 tok/s Generation, 135 tok/s Prefill, TTFT 80.768 ms (5 Laufe)Qwen3-30B-A3B-Instruc...Qwen3-30B-A3B-Thinking-2507 - 8,5 tok/s Generation, 74 tok/s Prefill, TTFT 134.321 ms (3 Laufe)Qwen3-30B-A3B-Thinkin...Nemotron-3-Nano-4B - 8,0 tok/s Generation, 63 tok/s Prefill, TTFT 139.289 ms (3 Laufe)Nemotron-3-Nano-4BQwen3-Coder-30B-A3B-Instruct - 6,7 tok/s Generation, 103 tok/s Prefill, TTFT 107.342 ms (3 Laufe)Qwen3-Coder-30B-A3B-I...Nemotron-3-Nano-30B-A3B - 6,6 tok/s Generation, 72 tok/s Prefill, TTFT 131.051 ms (3 Laufe)Nemotron-3-Nano-30B-A...Nemotron-Cascade-2-30B-A3B - 5,9 tok/s Generation, 72 tok/s Prefill, TTFT 130.288 ms (3 Laufe)Nemotron-Cascade-2-30...gpt-oss-120b - 5,3 tok/s Generation, 42 tok/s Prefill, TTFT 165.568 ms (3 Laufe)gpt-oss-120bNorth-Mini-Code-1.0 - 5,1 tok/s Generation, 89 tok/s Prefill, TTFT 113.797 ms (3 Laufe)North-Mini-Code-1.0Qwen3.6-35B-A3B - 4,3 tok/s Generation, 62 tok/s Prefill, TTFT 31.435 ms (1 Lauf)Qwen3.6-35B-A3BMeta-Llama-3.1-8B-Instruct - 3,6 tok/s Generation, 36 tok/s Prefill, TTFT 59.044 ms (1 Lauf)Meta-Llama-3.1-8B-Ins...MiniMax-M2.7 - 2,6 tok/s Generation, 24 tok/s Prefill, TTFT 193.311 ms (3 Laufe)MiniMax-M2.7Qwen2.5-72B-Instruct - 2,3 tok/s Generation, 81 tok/s Prefill, TTFT 569 ms (1 Lauf)Qwen2.5-72B-InstructGLM-4.5-Air - 2,1 tok/s Generation, 18 tok/s Prefill, TTFT 117.963 ms (1 Lauf)GLM-4.5-AirDeepSeek-V4-Flash-284B-A13B - 1,2 tok/s Generation, 14 tok/s Prefill, TTFT 148.315 ms (1 Lauf)DeepSeek-V4-Flash-284...OpenReasoning-Nemotron-32B - 1,1 tok/s Generation, 8 tok/s Prefill, TTFT 266.668 ms (1 Lauf)OpenReasoning-Nemotro...Seed-OSS-36B-Instruct - 1,0 tok/s Generation, 8 tok/s Prefill, TTFT 240.790 ms (1 Lauf)Seed-OSS-36B-InstructMiniMax-M2.5 - 0,8 tok/s Generation, 22 tok/s Prefill, TTFT 98.716 ms (1 Lauf)MiniMax-M2.5
gpt-oss-20b 70,9 tok/sQwen3-30B-A3B-Instruct-2507 26,0 tok/sQwen3-30B-A3B-Thinking-2507 8,5 tok/sNemotron-3-Nano-4B 8,0 tok/sQwen3-Coder-30B-A3B-Instruct 6,7 tok/sNemotron-3-Nano-30B-A3B 6,6 tok/sNemotron-Cascade-2-30B-A3B 5,9 tok/sgpt-oss-120b 5,3 tok/sNorth-Mini-Code-1.0 5,1 tok/sQwen3.6-35B-A3B 4,3 tok/sMeta-Llama-3.1-8B-Instruct 3,6 tok/sMiniMax-M2.7 2,6 tok/sQwen2.5-72B-Instruct 2,3 tok/sGLM-4.5-Air 2,1 tok/sDeepSeek-V4-Flash-284B-A13B 1,2 tok/sOpenReasoning-Nemotron-32B 1,1 tok/sSeed-OSS-36B-Instruct 1,0 tok/sMiniMax-M2.5 0,8 tok/s

ENGnach Engine

91,668,745,822,90,070758187Prefill (tok/s)Generation (tok/s)llama.cpp - 70,9 tok/s Generation, 75 tok/s Prefill, TTFT 125.863 ms (42 Laufe)llama.cppunbekannt - 2,3 tok/s Generation, 81 tok/s Prefill, TTFT 569 ms (1 Lauf)unbekannt
llama.cpp 70,9 tok/sunbekannt 2,3 tok/s

CPUnach Prozessor

89,266,944,622,30,03688140192Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 70,9 tok/s Generation, 164 tok/s Prefill, TTFT 56.674 ms (5 Laufe)AMD Ryzen Threadrippe...Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 14,5 tok/s Generation, 64 tok/s Prefill, TTFT 131.670 ms (38 Laufe)Intel(R) Xeon(R) CPU ...
AMD Ryzen Threadripper PRO 7955WX 16-Cores 70,9 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 14,5 tok/s
Durchsatz & Latenz

Performancebenchmark

43 veroeffentlichte Performance-Läufe auf Keine GPU (CPU-only).

Im Leaderboard →
Messwert:
Größe
#Modell / HerstellerMesswerteParallelGPU / CPU / RAMRuntime
1gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
70,85 tok/s TG
Prefill 154 · TTFT 129.121 ms
10×Keine GPU (CPU-only)AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawMXFP4Details →
2gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
53,48 tok/s TG
Prefill 153 · TTFT 64.583 ms
5×Keine GPU (CPU-only)AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawMXFP4Details →
3gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
28,43 tok/s TG
Prefill 143 · TTFT 13.839 ms
1×Keine GPU (CPU-only)AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawMXFP4Details →
4Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
25,98 tok/s TG
Prefill 218 · TTFT 59.755 ms
5×Keine GPU (CPU-only)AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_MDetails →
5Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
24,50 tok/s TG
Prefill 152 · TTFT 16.071 ms
1×Keine GPU (CPU-only)AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_MDetails →
6gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
14,47 tok/s TG
Prefill 97 · TTFT 222.547 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
7gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
9,77 tok/s TG
Prefill 89 · TTFT 119.492 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
8Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
8,52 tok/s TG
Prefill 71 · TTFT 152.830 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
9Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
7,97 tok/s TG
Prefill 72 · TTFT 153.653 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
10Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
7,14 tok/s TG
Prefill 69 · TTFT 35.318 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
11Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
6,74 tok/s TG
Prefill 74 · TTFT 32.942 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
12Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
6,64 tok/s TG
Prefill 73 · TTFT 33.548 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
13Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
6,60 tok/s TG
Prefill 73 · TTFT 150.849 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
14gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
6,46 tok/s TG
Prefill 79 · TTFT 25.000 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
15Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
6,09 tok/s TG
Prefill 100 · TTFT 121.223 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
16Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
6,05 tok/s TG
Prefill 104 · TTFT 116.729 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
17Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
5,88 tok/s TG
Prefill 61 · TTFT 35.422 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
18Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
5,86 tok/s TG
Prefill 61 · TTFT 35.481 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
19Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
5,33 tok/s TG
Prefill 74 · TTFT 150.609 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
20gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
5,29 tok/s TG
Prefill 56 · TTFT 189.966 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
21North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
5,05 tok/s TG
Prefill 71 · TTFT 28.002 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
22Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
4,94 tok/s TG
Prefill 41 · TTFT 62.079 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
23gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
4,46 tok/s TG
Prefill 50 · TTFT 39.304 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
24Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
4,29 tok/s TG
Prefill 62 · TTFT 31.435 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
25North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
4,20 tok/s TG
Prefill 86 · TTFT 127.307 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
26Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,55 tok/s TG
Prefill 36 · TTFT 59.044 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
27North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,16 tok/s TG
Prefill 109 · TTFT 186.084 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
28MiniMax-M2.7230BMiniMax PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
2,62 tok/s TG
Prefill 15 · TTFT 156.050 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
29Qwen2.5-72B-Instruct72BQwen (Alibaba) Performancebenchmark
2,28 tok/s TG
Prefill 81 · TTFT 569 ms
1×Keine GPU (CPU-only)51x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMgodclawDetails →
30GLM-4.5-Air106BZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
2,13 tok/s TG
Prefill 18 · TTFT 117.963 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
31DeepSeek-V4-Flash-284B-A13B284BDeepSeek PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,20 tok/s TG
Prefill 14 · TTFT 148.315 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawUD-Q4_K_XLDetails →
32OpenReasoning-Nemotron-32B32BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,10 tok/s TG
Prefill 8 · TTFT 266.668 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
33Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,04 tok/s TG
Prefill 137 · TTFT 171.473 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
34Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,99 tok/s TG
Prefill 130 · TTFT 172.354 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
35Seed-OSS-36B-Instruct36BByteDance Seed PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,97 tok/s TG
Prefill 8 · TTFT 240.790 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
36MiniMax-M2.5230BMiniMax PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,84 tok/s TG
Prefill 22 · TTFT 98.716 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
37Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,58 tok/s TG
Prefill 77 · TTFT 216.585 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
38Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,27 tok/s TG
Prefill 81 · TTFT 206.882 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
39Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,27 tok/s TG
Prefill 82 · TTFT 204.776 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
40Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,25 tok/s TG
Prefill 75 · TTFT 202.135 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
41gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,05 tok/s TG
Prefill 20 · TTFT 267.436 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
42MiniMax-M2.7230BMiniMax PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,04 tok/s TG
Prefill 29 · TTFT 211.132 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
43MiniMax-M2.7230BMiniMax PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,03 tok/s TG
Prefill 28 · TTFT 212.753 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
Agent- & Chat-Bewertung

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf Keine GPU (CPU-only).

Im Leaderboard →
Noch keine Harnessbenchmarks auf dieser Hardware.

← Alle Hardware

Technische Daten

Technische Daten – Keine GPU (CPU-only)

HerstellerOther
Beste Generation70,9 tok/s
Bester Prefill218 tok/s
Modelle18
Messläufe (Performance)43