Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Anmelden Registrieren
Beta
🧮
Mainboard

ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE

ASUS2 CPUs2370 Benchmarks⚡ 25 W Idle · 80 W Max
CPUs
2
Modelle
61
Benchmarks
2370
Beste Generation
2.143,6 tok/s
🏆
gemma-4-E2B-it läuft am schnellsten auf diesem Board · 2.143,6 tok/s
61 Modelle mit Performance-Daten getestet

Top-Modelle nach Token-Generierung

Bester gemessener Generierungs-Durchsatz je Modell auf ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE (tok/s) – klicken für Leaderboard-Filter.

gemma-4-E2B-it5B
2.143,6 tok/s
Nemotron-3-Nano-4B4B
1.937,7 tok/s
gpt-oss-20b20B
1.835,7 tok/s
Ornith-1.0-35B35B
1.799,4 tok/s
Nemotron-Cascade-2-30B-A3B30B
1.655,2 tok/s
Nemotron-3-Nano-30B-A3B30B
1.654,6 tok/s
Nemotron-3-Nano-Omni-30B-A3B-Reasoning30B
1.651,0 tok/s
Laguna-XS-2.1
1.629,9 tok/s
Qwen3-Coder-30B-A3B-Instruct30B
1.545,3 tok/s
Qwen3-30B-A3B-Thinking-250730B
1.521,4 tok/s
Qwen3-30B-A3B-Instruct-250730B
1.515,7 tok/s
Qwen3-Omni-30B-A3B-Thinking30B
1.512,4 tok/s
Anzeige
Modell-Vergleich

Getestete Modelle im Vergleich

Jede Blase ist ein Modell auf ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE – Position: Prompt-Verarbeitung (X) × Ausgabe-Geschwindigkeit (Y), Blasengröße: Anzahl Messläufe. Naeher an der oberen rechten Ecke = schneller.

MODnach Modell

2.7852.0891.3936960,006.95313.90620.859Prefill (tok/s)Generation (tok/s)gemma-4-E2B-it - 2.143,6 tok/s Generation, 16.830 tok/s Prefill, TTFT 1.967 ms (30 Laufe)gemma-4-E2B-itNemotron-3-Nano-4B - 1.937,7 tok/s Generation, 8.908 tok/s Prefill, TTFT 3.715 ms (34 Laufe)Nemotron-3-Nano-4Bgpt-oss-20b - 1.835,7 tok/s Generation, 6.778 tok/s Prefill, TTFT 14.338 ms (60 Laufe)gpt-oss-20bOrnith-1.0-35B - 1.799,4 tok/s Generation, 3.374 tok/s Prefill, TTFT 28.163 ms (24 Laufe)Ornith-1.0-35BNemotron-Cascade-2-30B-A3B - 1.655,2 tok/s Generation, 6.116 tok/s Prefill, TTFT 17.706 ms (43 Laufe)Nemotron-Cascade-2-30...Nemotron-3-Nano-30B-A3B - 1.654,6 tok/s Generation, 5.643 tok/s Prefill, TTFT 13.430 ms (61 Laufe)Nemotron-3-Nano-30B-A...Nemotron-3-Nano-Omni-30B-A3B-Reasoning - 1.651,0 tok/s Generation, 6.584 tok/s Prefill, TTFT 15.389 ms (49 Laufe)Nemotron-3-Nano-Omni-...Laguna-XS-2.1 - 1.629,9 tok/s Generation, 10.402 tok/s Prefill, TTFT 12.497 ms (76 Laufe)Laguna-XS-2.1Qwen3-Coder-30B-A3B-Instruct - 1.545,3 tok/s Generation, 10.166 tok/s Prefill, TTFT 13.581 ms (72 Laufe)Qwen3-Coder-30B-A3B-I...Qwen3-30B-A3B-Thinking-2507 - 1.521,4 tok/s Generation, 9.721 tok/s Prefill, TTFT 15.308 ms (70 Laufe)Qwen3-30B-A3B-Thinkin...Qwen3-30B-A3B-Instruct-2507 - 1.515,7 tok/s Generation, 9.649 tok/s Prefill, TTFT 15.108 ms (73 Laufe)Qwen3-30B-A3B-Instruc...Qwen3-Omni-30B-A3B-Thinking - 1.512,4 tok/s Generation, 9.490 tok/s Prefill, TTFT 21.465 ms (49 Laufe)Qwen3-Omni-30B-A3B-Th...Qwen3-VL-30B-A3B-Instruct - 1.505,0 tok/s Generation, 10.834 tok/s Prefill, TTFT 15.173 ms (65 Laufe)Qwen3-VL-30B-A3B-Inst...North-Mini-Code-1.0 - 1.492,4 tok/s Generation, 10.246 tok/s Prefill, TTFT 17.709 ms (52 Laufe)North-Mini-Code-1.0Gemma-4-26B-A4B-it - 1.479,9 tok/s Generation, 10.657 tok/s Prefill, TTFT 2.347 ms (45 Laufe)Gemma-4-26B-A4B-itMeta-Llama-3.1-8B-Instruct - 1.433,0 tok/s Generation, 10.975 tok/s Prefill, TTFT 3.362 ms (49 Laufe)Meta-Llama-3.1-8B-Ins...gemma-4-E4B-it - 1.423,3 tok/s Generation, 7.672 tok/s Prefill, TTFT 2.431 ms (12 Laufe)gemma-4-E4B-itQwen3.5-35B-A3B - 1.398,4 tok/s Generation, 7.005 tok/s Prefill, TTFT 11.724 ms (68 Laufe)Qwen3.5-35B-A3BQwen3.6-35B-A3B - 1.367,3 tok/s Generation, 6.964 tok/s Prefill, TTFT 11.395 ms (71 Laufe)Qwen3.6-35B-A3BQwen-AgentWorld-35B-A3B - 1.363,4 tok/s Generation, 6.059 tok/s Prefill, TTFT 14.248 ms (54 Laufe)Qwen-AgentWorld-35B-A...Ornith-1.0-9B - 1.349,7 tok/s Generation, 7.292 tok/s Prefill, TTFT 3.802 ms (51 Laufe)Ornith-1.0-9Bgpt-oss-120b - 1.229,7 tok/s Generation, 3.575 tok/s Prefill, TTFT 36.983 ms (25 Laufe)gpt-oss-120bQwen3-Coder-Next - 1.147,5 tok/s Generation, 6.457 tok/s Prefill, TTFT 26.967 ms (41 Laufe)Qwen3-Coder-Nextgemma-4-12B-it - 1.041,8 tok/s Generation, 6.135 tok/s Prefill, TTFT 3.672 ms (44 Laufe)gemma-4-12B-itMinistral-3-14B-Reasoning-2512 - 911,6 tok/s Generation, 5.685 tok/s Prefill, TTFT 5.263 ms (51 Laufe)Ministral-3-14B-Reaso...Laguna-S-2.1-INT4 - 779,8 tok/s Generation, 4.034 tok/s Prefill, TTFT 42.467 ms (43 Laufe)Laguna-S-2.1-INT4Magistral-Small-2509 - 637,2 tok/s Generation, 2.044 tok/s Prefill, TTFT 5.463 ms (54 Laufe)Magistral-Small-2509Ornith-1.5-35B-A3B - 626,4 tok/s Generation, 9.235 tok/s Prefill, TTFT 2.559 ms (18 Laufe)Ornith-1.5-35B-A3BGLM-4.5-Air - 615,3 tok/s Generation, 3.590 tok/s Prefill, TTFT 29.727 ms (29 Laufe)GLM-4.5-AirDevstral-Small-2507 - 572,2 tok/s Generation, 5.832 tok/s Prefill, TTFT 6.475 ms (54 Laufe)Devstral-Small-2507Devstral-Small-2-24B-Instruct-2512 - 569,7 tok/s Generation, 4.344 tok/s Prefill, TTFT 7.926 ms (51 Laufe)Devstral-Small-2-24B-...Qwen3.5-122B-A10B - 564,6 tok/s Generation, 2.956 tok/s Prefill, TTFT 15.851 ms (21 Laufe)Qwen3.5-122B-A10BCodestral-22B-v0.1 - 559,4 tok/s Generation, 3.424 tok/s Prefill, TTFT 10.149 ms (42 Laufe)Codestral-22B-v0.1MiniMax-M2.5 - 551,0 tok/s Generation, 2.205 tok/s Prefill, TTFT 45.313 ms (39 Laufe)MiniMax-M2.5MiniMax-M2.7 - 548,6 tok/s Generation, 1.224 tok/s Prefill, TTFT 67.296 ms (20 Laufe)MiniMax-M2.7minimax-m2-awq - 547,9 tok/s Generation, 3.894 tok/s Prefill, TTFT 9.312 ms (3 Laufe)minimax-m2-awqOrnith-1.5-9B - 472,2 tok/s Generation, 4.350 tok/s Prefill, TTFT 3.813 ms (12 Laufe)Ornith-1.5-9BQwen3.6-27B - 464,1 tok/s Generation, 2.336 tok/s Prefill, TTFT 12.736 ms (45 Laufe)Qwen3.6-27BQwen3.8-27B - 426,5 tok/s Generation, 2.903 tok/s Prefill, TTFT 2.696 ms (51 Laufe)Qwen3.8-27BNemotron-3-Super-120B-A12B - 423,4 tok/s Generation, 1.223 tok/s Prefill, TTFT 65.414 ms (29 Laufe)Nemotron-3-Super-120B...Qwen2.5-Coder-32B-Instruct - 412,8 tok/s Generation, 3.222 tok/s Prefill, TTFT 25.822 ms (63 Laufe)Qwen2.5-Coder-32B-Ins...Qwen2.5-32B-Instruct-AWQ - 412,6 tok/s Generation, 2.820 tok/s Prefill, TTFT 54.516 ms (28 Laufe)Qwen2.5-32B-Instruct-...OpenReasoning-Nemotron-32B - 411,7 tok/s Generation, 2.255 tok/s Prefill, TTFT 45.320 ms (31 Laufe)OpenReasoning-Nemotro...DeepSeek-V4-Flash-284B-A13B - 385,9 tok/s Generation, 806 tok/s Prefill, TTFT 108.517 ms (16 Laufe)DeepSeek-V4-Flash-284...Seed-OSS-36B-Instruct - 383,9 tok/s Generation, 2.210 tok/s Prefill, TTFT 41.174 ms (55 Laufe)Seed-OSS-36B-InstructLaguna-M.1 - 337,6 tok/s Generation, 1.174 tok/s Prefill, TTFT 102.619 ms (22 Laufe)Laguna-M.1Llama-3.3-Nemotron-Super-49B-v1.5 - 303,0 tok/s Generation, 1.563 tok/s Prefill, TTFT 101.042 ms (30 Laufe)Llama-3.3-Nemotron-Su...Nemotron-3.5-Lightning-30B-A3B - 290,3 tok/s Generation, 6.619 tok/s Prefill, TTFT 679 ms (27 Laufe)Nemotron-3.5-Lightnin...Gemma-4-26B-A4B - 264,1 tok/s Generation, 4.323 tok/s Prefill, TTFT 2.385 ms (6 Laufe)Gemma-4-26B-A4Bgemma-4-31B-it - 251,1 tok/s Generation, 2.043 tok/s Prefill, TTFT 9.985 ms (38 Laufe)gemma-4-31B-itMistral-Small-3.1-24B-Instruct-2503 - 214,9 tok/s Generation, 3.589 tok/s Prefill, TTFT 3.702 ms (43 Laufe)Mistral-Small-3.1-24B...Qwen2.5-72B-Instruct - 203,8 tok/s Generation, 1.144 tok/s Prefill, TTFT 161.966 ms (18 Laufe)Qwen2.5-72B-InstructNemotron-H-47B-Reasoning-128K - 203,5 tok/s Generation, 419 tok/s Prefill, TTFT 81.762 ms (45 Laufe)Nemotron-H-47B-Reason...Muse-Glimmer-30B - 199,1 tok/s Generation, 2.152 tok/s Prefill, TTFT 2.455 ms (9 Laufe)Muse-Glimmer-30BLing-3.0-flash - 160,2 tok/s Generation, 1.407 tok/s Prefill, TTFT 6.543 ms (23 Laufe)Ling-3.0-flashcommand-a-reasoning-08-2025 - 134,9 tok/s Generation, 1.415 tok/s Prefill, TTFT 32.031 ms (26 Laufe)command-a-reasoning-0...Devstral-2-123B-Instruct-2512 - 123,5 tok/s Generation, 585 tok/s Prefill, TTFT 114.317 ms (38 Laufe)Devstral-2-123B-Instr...Llama-3.1-Nemotron-Ultra-253B-v1 - 62,1 tok/s Generation, 218 tok/s Prefill, TTFT 331.677 ms (23 Laufe)Llama-3.1-Nemotron-Ul...Mistral-Small-4-119B-2603 - 58,5 tok/s Generation, 510 tok/s Prefill, TTFT 107.602 ms (11 Laufe)Mistral-Small-4-119B-...DeepSeek-V4-Flash - 20,6 tok/s Generation, 167 tok/s Prefill, TTFT 65.962 ms (15 Laufe)DeepSeek-V4-FlashMistral-Medium-3.5-128B - 5,8 tok/s Generation, 56 tok/s Prefill, TTFT 189.596 ms (14 Laufe)Mistral-Medium-3.5-12...
gemma-4-E2B-it 2.143,6 tok/sNemotron-3-Nano-4B 1.937,7 tok/sgpt-oss-20b 1.835,7 tok/sOrnith-1.0-35B 1.799,4 tok/sNemotron-Cascade-2-30B-A3B 1.655,2 tok/sNemotron-3-Nano-30B-A3B 1.654,6 tok/sNemotron-3-Nano-Omni-30B-A3B-Reasoning 1.651,0 tok/sLaguna-XS-2.1 1.629,9 tok/sQwen3-Coder-30B-A3B-Instruct 1.545,3 tok/sQwen3-30B-A3B-Thinking-2507 1.521,4 tok/sQwen3-30B-A3B-Instruct-2507 1.515,7 tok/sQwen3-Omni-30B-A3B-Thinking 1.512,4 tok/sQwen3-VL-30B-A3B-Instruct 1.505,0 tok/sNorth-Mini-Code-1.0 1.492,4 tok/sGemma-4-26B-A4B-it 1.479,9 tok/sMeta-Llama-3.1-8B-Instruct 1.433,0 tok/sgemma-4-E4B-it 1.423,3 tok/sQwen3.5-35B-A3B 1.398,4 tok/sQwen3.6-35B-A3B 1.367,3 tok/sQwen-AgentWorld-35B-A3B 1.363,4 tok/sOrnith-1.0-9B 1.349,7 tok/sgpt-oss-120b 1.229,7 tok/sQwen3-Coder-Next 1.147,5 tok/sgemma-4-12B-it 1.041,8 tok/sMinistral-3-14B-Reasoning-2512 911,6 tok/sLaguna-S-2.1-INT4 779,8 tok/sMagistral-Small-2509 637,2 tok/sOrnith-1.5-35B-A3B 626,4 tok/sGLM-4.5-Air 615,3 tok/sDevstral-Small-2507 572,2 tok/sDevstral-Small-2-24B-Instruct-2512 569,7 tok/sQwen3.5-122B-A10B 564,6 tok/sCodestral-22B-v0.1 559,4 tok/sMiniMax-M2.5 551,0 tok/sMiniMax-M2.7 548,6 tok/sminimax-m2-awq 547,9 tok/sOrnith-1.5-9B 472,2 tok/sQwen3.6-27B 464,1 tok/sQwen3.8-27B 426,5 tok/sNemotron-3-Super-120B-A12B 423,4 tok/sQwen2.5-Coder-32B-Instruct 412,8 tok/sQwen2.5-32B-Instruct-AWQ 412,6 tok/sOpenReasoning-Nemotron-32B 411,7 tok/sDeepSeek-V4-Flash-284B-A13B 385,9 tok/sSeed-OSS-36B-Instruct 383,9 tok/sLaguna-M.1 337,6 tok/sLlama-3.3-Nemotron-Super-49B-v1.5 303,0 tok/sNemotron-3.5-Lightning-30B-A3B 290,3 tok/sGemma-4-26B-A4B 264,1 tok/sgemma-4-31B-it 251,1 tok/sMistral-Small-3.1-24B-Instruct-2503 214,9 tok/sQwen2.5-72B-Instruct 203,8 tok/sNemotron-H-47B-Reasoning-128K 203,5 tok/sMuse-Glimmer-30B 199,1 tok/sLing-3.0-flash 160,2 tok/scommand-a-reasoning-08-2025 134,9 tok/sDevstral-2-123B-Instruct-2512 123,5 tok/sLlama-3.1-Nemotron-Ultra-253B-v1 62,1 tok/sMistral-Small-4-119B-2603 58,5 tok/sDeepSeek-V4-Flash 20,6 tok/sMistral-Medium-3.5-128B 5,8 tok/s

Prozessoren auf diesem Board

CPUAMD Ryzen Threadripper PRO 7955WX 16-CoresAMD · 1852 Läufe1.568,0 tok/s CPUAMD Ryzen Threadripper PRO 9965WX 24-CoresAMD · 518 Läufe2.143,6 tok/s

Grafikkarten auf diesem Board

GPU3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionNVIDIA · 518 Läufe2.143,6 tok/s GPU2x NVIDIA RTX A6000NVIDIA · 992 Läufe1.568,0 tok/s GPU4x AMD Radeon AI PRO R9700AMD · 855 Läufe667,0 tok/s

Getestete Modelle

Mgemma-4-E2B-it5BGoogle · 30 Läufe MNemotron-3-Nano-4B4BNVIDIA · 34 Läufe Mgpt-oss-20b20BOpenAI · 60 Läufe MOrnith-1.0-35B35BDeepReinforce · 24 Läufe MNemotron-Cascade-2-30B-A3B30BNVIDIA · 43 Läufe MNemotron-3-Nano-30B-A3B30BNVIDIA · 61 Läufe MNemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA · 49 Läufe MLaguna-XS-2.1Poolside · 76 Läufe MQwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) · 72 Läufe MQwen3-30B-A3B-Thinking-250730BQwen (Alibaba) · 70 Läufe MQwen3-30B-A3B-Instruct-250730BQwen (Alibaba) · 73 Läufe MQwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) · 49 Läufe MQwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) · 65 Läufe MNorth-Mini-Code-1.0Cohere · 52 Läufe MGemma-4-26B-A4B-it26BGoogle · 45 Läufe MMeta-Llama-3.1-8B-Instruct8BMeta · 49 Läufe Mgemma-4-E4B-it8BGoogle · 12 Läufe MQwen3.5-35B-A3B35BQwen (Alibaba) · 68 Läufe MQwen3.6-35B-A3B35BQwen (Alibaba) · 71 Läufe MQwen-AgentWorld-35B-A3B35BQwen (Alibaba) · 54 Läufe MOrnith-1.0-9B9BDeepReinforce · 51 Läufe Mgpt-oss-120b120BOpenAI · 25 Läufe MQwen3-Coder-NextQwen (Alibaba) · 41 Läufe Mgemma-4-12B-it12BGoogle · 44 Läufe MMinistral-3-14B-Reasoning-251214BMistral AI · 51 Läufe MLaguna-S-2.1-INT4Poolside · 43 Läufe MMagistral-Small-250924BMistral AI · 54 Läufe MOrnith-1.5-35B-A3B35BDeepReinforce · 18 Läufe MGLM-4.5-Air106BZ.ai (Zhipu) · 29 Läufe MDevstral-Small-250724BMistral AI · 54 Läufe MDevstral-Small-2-24B-Instruct-251224BMistral AI · 51 Läufe MQwen3.5-122B-A10B122BQwen (Alibaba) · 21 Läufe MCodestral-22B-v0.122BMistral AI · 42 Läufe MMiniMax-M2.5230BMiniMax · 48 Läufe MMiniMax-M2.7230BMiniMax · 20 Läufe Mminimax-m2-awq230BMiniMax · 3 Läufe MOrnith-1.5-9B9BDeepReinforce · 12 Läufe MQwen3.6-27B27BQwen (Alibaba) · 45 Läufe MQwen3.8-27B27BQwen (Alibaba) · 51 Läufe MNemotron-3-Super-120B-A12B120BNVIDIA · 29 Läufe MQwen2.5-Coder-32B-Instruct32BQwen (Alibaba) · 63 Läufe MQwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) · 28 Läufe MOpenReasoning-Nemotron-32B32BNVIDIA · 31 Läufe MDeepSeek-V4-Flash-284B-A13B284BDeepSeek · 16 Läufe MSeed-OSS-36B-Instruct36BByteDance Seed · 55 Läufe MLaguna-M.1Poolside · 22 Läufe MLlama-3.3-Nemotron-Super-49B-v1.549BNVIDIA · 30 Läufe MNemotron-3.5-Lightning-30B-A3B30BNVIDIA · 27 Läufe MGemma-4-26B-A4B26BGoogle · 6 Läufe Mgemma-4-31B-it31BGoogle · 38 Läufe MMistral-Small-3.1-24B-Instruct-250324BMistral AI · 43 Läufe MQwen2.5-72B-Instruct72BQwen (Alibaba) · 18 Läufe MNemotron-H-47B-Reasoning-128K47BNVIDIA · 45 Läufe MMuse-Glimmer-30B30BMeta · 9 Läufe MLing-3.0-flash127.5BinclusionAI · 23 Läufe Mcommand-a-reasoning-08-2025111BCohere · 26 Läufe MDevstral-2-123B-Instruct-2512123BMistral AI · 38 Läufe MLlama-3.1-Nemotron-Ultra-253B-v1253BNVIDIA · 23 Läufe MMistral-Small-4-119B-2603119BMistral AI · 11 Läufe MDeepSeek-V4-Flash290.9BDeepSeek · 15 Läufe MMistral-Medium-3.5-128B128BMistral AI · 14 Läufe

Genutzte Betriebssysteme

🖥Ubuntu 26.04 LTS (Kernel 7.0.0-27-generic)
Durchsatz & Latenz

Performancebenchmark

80 veroeffentlichte Performance-Läufe auf ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE.

Im Leaderboard →
Messwert:
Größe
#Modell / HerstellerMesswerteParallelGPU / CPU / RAMRuntime
1gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
2.143,55 tok/s TG
Prefill 13.632 · TTFT 4.819 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
2Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.937,67 tok/s TG
Prefill 9.452 · TTFT 6.288 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
3Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.911,59 tok/s TG
Prefill 10.116 · TTFT 6.245 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
4Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.896,98 tok/s TG
Prefill 10.984 · TTFT 6.227 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
5gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.835,73 tok/s TG
Prefill 15.972 · TTFT 5.760 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
6Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.830,31 tok/s TG
Prefill 9.399 · TTFT 6.598 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
7gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.819,53 tok/s TG
Prefill 19.732 · TTFT 5.578 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
8gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.801,97 tok/s TG
Prefill 18.226 · TTFT 5.605 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
9Ornith-1.0-35B35BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.799,41 tok/s TG
Prefill 9.192 · TTFT 8.876 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
10gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.742,13 tok/s TG
Prefill 12.852 · TTFT 6.156 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
11Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.655,21 tok/s TG
Prefill 10.591 · TTFT 7.004 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
12Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.654,57 tok/s TG
Prefill 10.472 · TTFT 7.000 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
13Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.650,98 tok/s TG
Prefill 11.364 · TTFT 6.872 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
14Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.650,72 tok/s TG
Prefill 11.398 · TTFT 6.887 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
15Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.649,85 tok/s TG
Prefill 10.323 · TTFT 7.066 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
16Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.629,91 tok/s TG
Prefill 11.384 · TTFT 7.322 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
17Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.620,45 tok/s TG
Prefill 10.729 · TTFT 7.428 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
18Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.620,41 tok/s TG
Prefill 12.519 · TTFT 7.197 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
19Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.615,26 tok/s TG
Prefill 13.041 · TTFT 7.166 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
20Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.611,02 tok/s TG
Prefill 12.725 · TTFT 7.223 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
21Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.609,12 tok/s TG
Prefill 10.883 · TTFT 7.452 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
22Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.608,39 tok/s TG
Prefill 11.312 · TTFT 7.410 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
23Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.607,66 tok/s TG
Prefill 10.675 · TTFT 7.505 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
24Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.606,11 tok/s TG
Prefill 12.690 · TTFT 7.203 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
25gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.567,98 tok/s TG
Prefill 55.260 · TTFT 492 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8Details →
26Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.554,46 tok/s TG
Prefill 7.954 · TTFT 8.418 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
27Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.554,37 tok/s TG
Prefill 10.928 · TTFT 6.920 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
28Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.545,29 tok/s TG
Prefill 19.346 · TTFT 6.758 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
29Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.542,64 tok/s TG
Prefill 7.398 · TTFT 8.118 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
30Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.540,50 tok/s TG
Prefill 7.349 · TTFT 8.077 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
31Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.534,12 tok/s TG
Prefill 7.243 · TTFT 8.145 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
32Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.533,70 tok/s TG
Prefill 6.831 · TTFT 8.783 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
33Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.532,89 tok/s TG
Prefill 7.482 · TTFT 8.633 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
34Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.531,89 tok/s TG
Prefill 17.119 · TTFT 6.936 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
35Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.521,37 tok/s TG
Prefill 12.779 · TTFT 7.364 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
36Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.518,42 tok/s TG
Prefill 15.383 · TTFT 7.173 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
37Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.515,72 tok/s TG
Prefill 20.491 · TTFT 6.859 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
38Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.512,43 tok/s TG
Prefill 14.637 · TTFT 7.246 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
39Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.511,01 tok/s TG
Prefill 11.948 · TTFT 7.503 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
40Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.507,51 tok/s TG
Prefill 16.412 · TTFT 7.065 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
41Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.505,03 tok/s TG
Prefill 19.292 · TTFT 6.959 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
42Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.498,91 tok/s TG
Prefill 15.825 · TTFT 7.173 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
43North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.492,41 tok/s TG
Prefill 10.415 · TTFT 7.570 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
44North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.490,67 tok/s TG
Prefill 10.879 · TTFT 7.498 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
45Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.485,14 tok/s TG
Prefill 44.171 · TTFT 717 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8Details →
46North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.482,54 tok/s TG
Prefill 11.096 · TTFT 7.518 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
47Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.479,91 tok/s TG
Prefill 8.811 · TTFT 7.965 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_XLDetails →
48Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.479,41 tok/s TG
Prefill 6.414 · TTFT 8.654 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_XLDetails →
49North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.477,72 tok/s TG
Prefill 7.220 · TTFT 8.321 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
50Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.466,18 tok/s TG
Prefill 8.044 · TTFT 8.213 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_XLDetails →
51Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.465,26 tok/s TG
Prefill 8.251 · TTFT 8.474 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
52Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.458,58 tok/s TG
Prefill 7.808 · TTFT 8.611 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
53Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.455,41 tok/s TG
Prefill 11.267 · TTFT 7.904 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
54Ornith-1.0-35B35BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.447,27 tok/s TG
Prefill 8.138 · TTFT 7.915 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
55Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.436,00 tok/s TG
Prefill 10.085 · TTFT 8.120 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
56Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.432,98 tok/s TG
Prefill 21.012 · TTFT 6.892 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
57gemma-4-E4B-it8BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.423,31 tok/s TG
Prefill 10.739 · TTFT 6.965 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
58gemma-4-E4B-it8BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.421,79 tok/s TG
Prefill 12.418 · TTFT 6.980 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
59Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.420,15 tok/s TG
Prefill 10.691 · TTFT 8.165 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
60Ornith-1.0-35B35BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.400,99 tok/s TG
Prefill 6.038 · TTFT 8.703 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
61Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.398,38 tok/s TG
Prefill 8.247 · TTFT 8.094 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
62Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.389,23 tok/s TG
Prefill 7.940 · TTFT 8.056 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
63Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.383,23 tok/s TG
Prefill 17.796 · TTFT 7.072 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
64Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.367,32 tok/s TG
Prefill 9.899 · TTFT 8.047 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
65Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.363,39 tok/s TG
Prefill 9.248 · TTFT 8.137 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
66Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.361,67 tok/s TG
Prefill 9.538 · TTFT 7.854 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
67gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.359,09 tok/s TG
Prefill 47.158 · TTFT 587 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8Details →
68Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.349,73 tok/s TG
Prefill 11.193 · TTFT 7.579 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
69Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.348,63 tok/s TG
Prefill 6.479 · TTFT 8.949 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
70Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.341,33 tok/s TG
Prefill 8.440 · TTFT 8.344 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
71Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.338,40 tok/s TG
Prefill 8.627 · TTFT 8.328 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
72Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.309,27 tok/s TG
Prefill 10.749 · TTFT 7.401 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
73Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.267,62 tok/s TG
Prefill 13.497 · TTFT 8.310 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
74Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.243,85 tok/s TG
Prefill 5.117 · TTFT 9.159 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
75gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.238,26 tok/s TG
Prefill 21.843 · TTFT 905 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMvLLMgodclawDetails →
76Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.236,51 tok/s TG
Prefill 7.739 · TTFT 8.840 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
77gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.229,72 tok/s TG
Prefill 9.543 · TTFT 8.771 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
78gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.220,77 tok/s TG
Prefill 7.425 · TTFT 9.155 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
79gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.214,90 tok/s TG
Prefill 7.954 · TTFT 9.043 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawQ4_K_MDetails →
80Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.212,13 tok/s TG
Prefill 6.225 · TTFT 8.915 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
Agent- & Chat-Bewertung

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE.

Im Leaderboard →
Noch keine Harnessbenchmarks auf diesem Mainboard.

← Alle Hardware