Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
🧮
Mainboard

ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI

ASUS3 CPUs822 Benchmarks⚡ 10 W Idle
CPUs
3
Models
72
Benchmarks
822
Best generation
1.744,0 tok/s
🏆
gemma-4-E2B-it läuft am schnellsten auf diesem Board · 1.744,0 tok/s
72 Modelle mit Performance-Daten getestet

Top models by token generation

Bester gemessener Generierungs-Durchsatz je Modell auf ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI (tok/s) – klicken für Leaderboard-Filter.

gemma-4-E2B-it5B
1.744,0 tok/s
gpt-oss-20b20B
1.210,3 tok/s
NVIDIA-Nemotron-3-Nano-4B4B
1.197,0 tok/s
gemma-4-E4B-it8B
1.082,4 tok/s
Gemma-4-26B-A4B-it26B
1.009,0 tok/s
Meta-Llama-3.1-8B-Instruct8B
913,4 tok/s
Ornith-1.0-9B9B
883,4 tok/s
Llama-3.2-1B-Instruct1B
717,6 tok/s
gemma-4-12B-it12B
677,5 tok/s
Ministral-3-14B-Reasoning-251214B
590,0 tok/s
SmolLM2-1.7B-Instruct1.7B
531,7 tok/s
Qwen3-0.6B0.6B
495,5 tok/s
Anzeige
Model comparison

Tested models compared

Jede Blase ist ein Modell auf ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI – Position: Prompt-Verarbeitung (X) × Ausgabe-Geschwindigkeit (Y), Blasengröße: Anzahl Messläufe. Naeher an der oberen rechten Ecke = schneller.

MODnach Modell

2.2671.7001.1335670,0013.27926.55839.837Prefill (tok/s)Generation (tok/s)gemma-4-E2B-it - 1.744,0 tok/s Generation, 8.810 tok/s Prefill, TTFT 2.129 ms (25 Laufe)gemma-4-E2B-itgpt-oss-20b - 1.210,3 tok/s Generation, 3.625 tok/s Prefill, TTFT 4.938 ms (27 Laufe)gpt-oss-20bNVIDIA-Nemotron-3-Nano-4B - 1.197,0 tok/s Generation, 4.606 tok/s Prefill, TTFT 4.936 ms (3 Laufe)NVIDIA-Nemotron-3-Nan...gemma-4-E4B-it - 1.082,4 tok/s Generation, 9.183 tok/s Prefill, TTFT 2.840 ms (6 Laufe)gemma-4-E4B-itGemma-4-26B-A4B-it - 1.009,0 tok/s Generation, 2.819 tok/s Prefill, TTFT 4.072 ms (14 Laufe)Gemma-4-26B-A4B-itMeta-Llama-3.1-8B-Instruct - 913,4 tok/s Generation, 5.149 tok/s Prefill, TTFT 3.142 ms (29 Laufe)Meta-Llama-3.1-8B-Ins...Ornith-1.0-9B - 883,4 tok/s Generation, 2.786 tok/s Prefill, TTFT 4.246 ms (23 Laufe)Ornith-1.0-9BLlama-3.2-1B-Instruct - 717,6 tok/s Generation, 32.133 tok/s Prefill, TTFT 493 ms (6 Laufe)Llama-3.2-1B-Instructgemma-4-12B-it - 677,5 tok/s Generation, 1.821 tok/s Prefill, TTFT 8.906 ms (23 Laufe)gemma-4-12B-itMinistral-3-14B-Reasoning-2512 - 590,0 tok/s Generation, 2.722 tok/s Prefill, TTFT 5.836 ms (36 Laufe)Ministral-3-14B-Reaso...SmolLM2-1.7B-Instruct - 531,7 tok/s Generation, 30.326 tok/s Prefill, TTFT 600 ms (3 Laufe)SmolLM2-1.7B-InstructQwen3-0.6B - 495,5 tok/s Generation, 27.231 tok/s Prefill, TTFT 657 ms (5 Laufe)Qwen3-0.6BLaguna-XS-2.1 - 468,6 tok/s Generation, 1.793 tok/s Prefill, TTFT 20.831 ms (18 Laufe)Laguna-XS-2.1Llama-3.2-3B-Instruct - 465,7 tok/s Generation, 15.391 tok/s Prefill, TTFT 992 ms (6 Laufe)Llama-3.2-3B-InstructQwen-AgentWorld-35B-A3B - 451,0 tok/s Generation, 1.919 tok/s Prefill, TTFT 24.622 ms (6 Laufe)Qwen-AgentWorld-35B-A...Qwen3.6-35B-A3B - 450,5 tok/s Generation, 3.071 tok/s Prefill, TTFT 9.227 ms (36 Laufe)Qwen3.6-35B-A3BQwen3.5-35B-A3B - 447,0 tok/s Generation, 2.572 tok/s Prefill, TTFT 11.931 ms (24 Laufe)Qwen3.5-35B-A3BQwen3-1.7B - 445,2 tok/s Generation, 18.781 tok/s Prefill, TTFT 935 ms (6 Laufe)Qwen3-1.7BQwen2.5-7B-Instruct - 442,0 tok/s Generation, 9.575 tok/s Prefill, TTFT 1.732 ms (6 Laufe)Qwen2.5-7B-InstructLlama-3.1-Nemotron-Nano-4B-v1.1 - 419,4 tok/s Generation, 8.744 tok/s Prefill, TTFT 1.556 ms (6 Laufe)Llama-3.1-Nemotron-Na...Qwen2.5-3B-Instruct - 358,2 tok/s Generation, 15.665 tok/s Prefill, TTFT 1.104 ms (6 Laufe)Qwen2.5-3B-InstructQwen3-Coder-30B-A3B-Instruct - 324,9 tok/s Generation, 4.831 tok/s Prefill, TTFT 6.472 ms (24 Laufe)Qwen3-Coder-30B-A3B-I...gemma-2-2b-it - 322,9 tok/s Generation, 18.870 tok/s Prefill, TTFT 583 ms (3 Laufe)gemma-2-2b-itQwen3-4B - 320,4 tok/s Generation, 10.970 tok/s Prefill, TTFT 1.493 ms (6 Laufe)Qwen3-4BQwen3-8B - 315,2 tok/s Generation, 7.254 tok/s Prefill, TTFT 2.212 ms (6 Laufe)Qwen3-8BQwen3-30B-A3B-Instruct-2507 - 314,0 tok/s Generation, 3.645 tok/s Prefill, TTFT 8.245 ms (22 Laufe)Qwen3-30B-A3B-Instruc...North-Mini-Code-1.0 - 312,7 tok/s Generation, 2.478 tok/s Prefill, TTFT 10.557 ms (12 Laufe)North-Mini-Code-1.0Ornith-1.0-35B - 309,0 tok/s Generation, 1.551 tok/s Prefill, TTFT 12.490 ms (6 Laufe)Ornith-1.0-35BQwen3-Omni-30B-A3B-Thinking - 305,4 tok/s Generation, 3.011 tok/s Prefill, TTFT 12.685 ms (10 Laufe)Qwen3-Omni-30B-A3B-Th...Qwen3-30B-A3B-Thinking-2507 - 303,1 tok/s Generation, 3.676 tok/s Prefill, TTFT 9.698 ms (18 Laufe)Qwen3-30B-A3B-Thinkin...Phi-3.5-mini-instruct - 302,0 tok/s Generation, 13.699 tok/s Prefill, TTFT 1.150 ms (3 Laufe)Phi-3.5-mini-instructQwen3-VL-30B-A3B-Instruct - 301,6 tok/s Generation, 3.207 tok/s Prefill, TTFT 8.631 ms (22 Laufe)Qwen3-VL-30B-A3B-Inst...Qwen3-14B - 280,8 tok/s Generation, 4.723 tok/s Prefill, TTFT 3.358 ms (6 Laufe)Qwen3-14Bgemma-3n-E4B-it - 273,1 tok/s Generation, 3.847 tok/s Prefill, TTFT 2.646 ms (6 Laufe)gemma-3n-E4B-itNVIDIA-Nemotron-3-Nano-30B-A3B - 263,3 tok/s Generation, 688 tok/s Prefill, TTFT 27.273 ms (3 Laufe)NVIDIA-Nemotron-3-Nan...Nemotron-3-Nano-Omni-30B-A3B-Reasoning - 262,5 tok/s Generation, 700 tok/s Prefill, TTFT 27.130 ms (3 Laufe)Nemotron-3-Nano-Omni-...Nemotron-Cascade-2-30B-A3B - 262,4 tok/s Generation, 720 tok/s Prefill, TTFT 26.930 ms (3 Laufe)Nemotron-Cascade-2-30...gpt-oss-120b - 216,2 tok/s Generation, 639 tok/s Prefill, TTFT 39.542 ms (6 Laufe)gpt-oss-120bHuihui-Qwen3-VL-30B-A3B-Instruct-abliterated - 207,9 tok/s Generation, 4.513 tok/s Prefill, TTFT 2.485 ms (3 Laufe)Huihui-Qwen3-VL-30B-A...Ling-3.0-flash - 194,7 tok/s Generation, 1.079 tok/s Prefill, TTFT 21.150 ms (37 Laufe)Ling-3.0-flashMuse-Glimmer-30B - 182,7 tok/s Generation, 1.002 tok/s Prefill, TTFT 10.161 ms (3 Laufe)Muse-Glimmer-30BQwen2.5-32B-Instruct - 179,0 tok/s Generation, 1.375 tok/s Prefill, TTFT 28.437 ms (15 Laufe)Qwen2.5-32B-InstructQwen2.5-Coder-32B-Instruct - 178,5 tok/s Generation, 1.296 tok/s Prefill, TTFT 23.896 ms (21 Laufe)Qwen2.5-Coder-32B-Ins...Magistral-Small-2509 - 159,0 tok/s Generation, 1.279 tok/s Prefill, TTFT 9.683 ms (21 Laufe)Magistral-Small-2509Devstral-Small-2507 - 156,8 tok/s Generation, 2.562 tok/s Prefill, TTFT 14.297 ms (23 Laufe)Devstral-Small-2507Devstral-Small-2-24B-Instruct-2512 - 152,1 tok/s Generation, 1.589 tok/s Prefill, TTFT 11.786 ms (24 Laufe)Devstral-Small-2-24B-...glm-4.7-flash - 151,7 tok/s Generation, 3.752 tok/s Prefill, TTFT 3.439 ms (3 Laufe)glm-4.7-flashMistral-Small-3.1-24B-Instruct-2503 - 151,5 tok/s Generation, 1.926 tok/s Prefill, TTFT 7.771 ms (22 Laufe)Mistral-Small-3.1-24B...Codestral-22B-v0.1 - 147,5 tok/s Generation, 1.425 tok/s Prefill, TTFT 16.502 ms (30 Laufe)Codestral-22B-v0.1Qwen3.6-27B - 110,0 tok/s Generation, 690 tok/s Prefill, TTFT 32.232 ms (10 Laufe)Qwen3.6-27BQwen3-Coder-Next - 106,1 tok/s Generation, 309 tok/s Prefill, TTFT 67.849 ms (3 Laufe)Qwen3-Coder-Nextgemma-4-31B-it - 101,9 tok/s Generation, 351 tok/s Prefill, TTFT 52.767 ms (6 Laufe)gemma-4-31B-itGLM-4.5-Air - 99,5 tok/s Generation, 373 tok/s Prefill, TTFT 58.315 ms (12 Laufe)GLM-4.5-AirQwen3.5-122B-A10B - 96,5 tok/s Generation, 266 tok/s Prefill, TTFT 106.889 ms (17 Laufe)Qwen3.5-122B-A10BSeed-OSS-36B-Instruct - 88,6 tok/s Generation, 802 tok/s Prefill, TTFT 35.467 ms (12 Laufe)Seed-OSS-36B-InstructLlama-3_3-Nemotron-Super-49B-v1_5 - 71,0 tok/s Generation, 380 tok/s Prefill, TTFT 76.920 ms (6 Laufe)Llama-3_3-Nemotron-Su...Mistral-Small-4-119B-2603 - 62,3 tok/s Generation, 213 tok/s Prefill, TTFT 120.533 ms (3 Laufe)Mistral-Small-4-119B-...OpenReasoning-Nemotron-32B - 49,9 tok/s Generation, 621 tok/s Prefill, TTFT 94.653 ms (3 Laufe)OpenReasoning-Nemotro...Laguna-S-2.1 - 42,3 tok/s Generation, 139 tok/s Prefill, TTFT 136.435 ms (3 Laufe)Laguna-S-2.1Qwen3.8-Flash-Next - 35,4 tok/s Generation, 170 tok/s Prefill, TTFT 59.933 ms (9 Laufe)Qwen3.8-Flash-NextNVIDIA-Nemotron-3-Super-120B-A12B - 32,6 tok/s Generation, 88 tok/s Prefill, TTFT 156.105 ms (6 Laufe)NVIDIA-Nemotron-3-Sup...MiniMax-M2.5 - 22,5 tok/s Generation, 124 tok/s Prefill, TTFT 132.424 ms (18 Laufe)MiniMax-M2.5Nemotron-H-47B-Reasoning-128K - 20,4 tok/s Generation, 168 tok/s Prefill, TTFT 134.329 ms (3 Laufe)Nemotron-H-47B-Reason...minimax-m2 - 17,0 tok/s Generation, 100 tok/s Prefill, TTFT 162.821 ms (3 Laufe)minimax-m2Step-3.5-Flash - 16,8 tok/s Generation, 161 tok/s Prefill, TTFT 74.043 ms (3 Laufe)Step-3.5-FlashDeepSeek-V4-Flash-284B-A13B - 10,0 tok/s Generation, 69 tok/s Prefill, TTFT 132.055 ms (3 Laufe)DeepSeek-V4-Flash-284...Laguna-M.1 - 7,0 tok/s Generation, 60 tok/s Prefill, TTFT 116.585 ms (12 Laufe)Laguna-M.1command-a-reasoning-08-2025 - 6,7 tok/s Generation, 108 tok/s Prefill, TTFT 64.666 ms (3 Laufe)command-a-reasoning-0...Qwen2.5-72B-Instruct - 5,8 tok/s Generation, 159 tok/s Prefill, TTFT 42.383 ms (3 Laufe)Qwen2.5-72B-InstructDevstral-2-123B-Instruct-2512 - 4,5 tok/s Generation, 127 tok/s Prefill, TTFT 54.082 ms (3 Laufe)Devstral-2-123B-Instr...Mistral-Medium-3.5-128B - 4,2 tok/s Generation, 131 tok/s Prefill, TTFT 53.481 ms (3 Laufe)Mistral-Medium-3.5-12...Llama-3_1-Nemotron-Ultra-253B-v1 - 1,7 tok/s Generation, 45 tok/s Prefill, TTFT 141.946 ms (3 Laufe)Llama-3_1-Nemotron-Ul...
gemma-4-E2B-it 1.744,0 tok/sgpt-oss-20b 1.210,3 tok/sNVIDIA-Nemotron-3-Nano-4B 1.197,0 tok/sgemma-4-E4B-it 1.082,4 tok/sGemma-4-26B-A4B-it 1.009,0 tok/sMeta-Llama-3.1-8B-Instruct 913,4 tok/sOrnith-1.0-9B 883,4 tok/sLlama-3.2-1B-Instruct 717,6 tok/sgemma-4-12B-it 677,5 tok/sMinistral-3-14B-Reasoning-2512 590,0 tok/sSmolLM2-1.7B-Instruct 531,7 tok/sQwen3-0.6B 495,5 tok/sLaguna-XS-2.1 468,6 tok/sLlama-3.2-3B-Instruct 465,7 tok/sQwen-AgentWorld-35B-A3B 451,0 tok/sQwen3.6-35B-A3B 450,5 tok/sQwen3.5-35B-A3B 447,0 tok/sQwen3-1.7B 445,2 tok/sQwen2.5-7B-Instruct 442,0 tok/sLlama-3.1-Nemotron-Nano-4B-v1.1 419,4 tok/sQwen2.5-3B-Instruct 358,2 tok/sQwen3-Coder-30B-A3B-Instruct 324,9 tok/sgemma-2-2b-it 322,9 tok/sQwen3-4B 320,4 tok/sQwen3-8B 315,2 tok/sQwen3-30B-A3B-Instruct-2507 314,0 tok/sNorth-Mini-Code-1.0 312,7 tok/sOrnith-1.0-35B 309,0 tok/sQwen3-Omni-30B-A3B-Thinking 305,4 tok/sQwen3-30B-A3B-Thinking-2507 303,1 tok/sPhi-3.5-mini-instruct 302,0 tok/sQwen3-VL-30B-A3B-Instruct 301,6 tok/sQwen3-14B 280,8 tok/sgemma-3n-E4B-it 273,1 tok/sNVIDIA-Nemotron-3-Nano-30B-A3B 263,3 tok/sNemotron-3-Nano-Omni-30B-A3B-Reasoning 262,5 tok/sNemotron-Cascade-2-30B-A3B 262,4 tok/sgpt-oss-120b 216,2 tok/sHuihui-Qwen3-VL-30B-A3B-Instruct-abliterated 207,9 tok/sLing-3.0-flash 194,7 tok/sMuse-Glimmer-30B 182,7 tok/sQwen2.5-32B-Instruct 179,0 tok/sQwen2.5-Coder-32B-Instruct 178,5 tok/sMagistral-Small-2509 159,0 tok/sDevstral-Small-2507 156,8 tok/sDevstral-Small-2-24B-Instruct-2512 152,1 tok/sglm-4.7-flash 151,7 tok/sMistral-Small-3.1-24B-Instruct-2503 151,5 tok/sCodestral-22B-v0.1 147,5 tok/sQwen3.6-27B 110,0 tok/sQwen3-Coder-Next 106,1 tok/sgemma-4-31B-it 101,9 tok/sGLM-4.5-Air 99,5 tok/sQwen3.5-122B-A10B 96,5 tok/sSeed-OSS-36B-Instruct 88,6 tok/sLlama-3_3-Nemotron-Super-49B-v1_5 71,0 tok/sMistral-Small-4-119B-2603 62,3 tok/sOpenReasoning-Nemotron-32B 49,9 tok/sLaguna-S-2.1 42,3 tok/sQwen3.8-Flash-Next 35,4 tok/sNVIDIA-Nemotron-3-Super-120B-A12B 32,6 tok/sMiniMax-M2.5 22,5 tok/sNemotron-H-47B-Reasoning-128K 20,4 tok/sminimax-m2 17,0 tok/sStep-3.5-Flash 16,8 tok/sDeepSeek-V4-Flash-284B-A13B 10,0 tok/sLaguna-M.1 7,0 tok/scommand-a-reasoning-08-2025 6,7 tok/sQwen2.5-72B-Instruct 5,8 tok/sDevstral-2-123B-Instruct-2512 4,5 tok/sMistral-Medium-3.5-128B 4,2 tok/sLlama-3_1-Nemotron-Ultra-253B-v1 1,7 tok/s

Processors on this board

CPUAMD Ryzen Threadripper PRO 5975WX 32-CoresAMD · 621 Läufe1.744,0 tok/s CPUAMD Ryzen Threadripper PRO 3955WX 16-CoresAMD · 189 Läufe717,6 tok/s CPUAMD EPYC 7203P 8-Core ProcessorAMD · 12 Läufe194,7 tok/s

Graphics cards on this board

GPUNVIDIA GeForce RTX 5070 TiNVIDIA · 216 Läufe1.744,0 tok/s GPU2x AMD Radeon RX 7900 XTXAMD · 189 Läufe717,6 tok/s GPU2x AMD Radeon PRO W7800 48GBAMD · 164 Läufe702,9 tok/s GPU2x AMD Radeon PRO W7900 Dual SlotAMD · 241 Läufe344,1 tok/s GPU2x NVIDIA RTX A6000NVIDIA · 12 Läufe194,7 tok/s

Tested models

Mgemma-4-E2B-it5BGoogle · 25 Läufe Mgpt-oss-20b20BOpenAI · 27 Läufe MNVIDIA-Nemotron-3-Nano-4B4BNVIDIA · 3 Läufe Mgemma-4-E4B-it8BGoogle · 6 Läufe MGemma-4-26B-A4B-it26BGoogle · 14 Läufe MMeta-Llama-3.1-8B-Instruct8BMeta · 29 Läufe MOrnith-1.0-9B9BDeepReinforce · 23 Läufe MLlama-3.2-1B-Instruct1BMeta · 6 Läufe Mgemma-4-12B-it12BGoogle · 23 Läufe MMinistral-3-14B-Reasoning-251214BMistral AI · 36 Läufe MSmolLM2-1.7B-Instruct1.7BHuggingFaceTB · 3 Läufe MQwen3-0.6B0.6BQwen (Alibaba) · 5 Läufe MLaguna-XS-2.133.4BPoolside · 18 Läufe MLlama-3.2-3B-Instruct3BMeta · 6 Läufe MQwen-AgentWorld-35B-A3B35BQwen (Alibaba) · 6 Läufe MQwen3.6-35B-A3B35BQwen (Alibaba) · 36 Läufe MQwen3.5-35B-A3B35BQwen (Alibaba) · 24 Läufe MQwen3-1.7B1.7BQwen (Alibaba) · 6 Läufe MQwen2.5-7B-Instruct7BQwen (Alibaba) · 6 Läufe MLlama-3.1-Nemotron-Nano-4B-v1.14.5BNVIDIA · 6 Läufe MQwen2.5-3B-Instruct3BQwen (Alibaba) · 6 Läufe MQwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) · 24 Läufe Mgemma-2-2b-it2BGoogle · 3 Läufe MQwen3-4B4BQwen (Alibaba) · 6 Läufe MQwen3-8B8.2BQwen (Alibaba) · 6 Läufe MQwen3-30B-A3B-Instruct-250730BQwen (Alibaba) · 22 Läufe MNorth-Mini-Code-1.030.5BCohere · 12 Läufe MOrnith-1.0-35B35BDeepReinforce · 6 Läufe MQwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) · 10 Läufe MQwen3-30B-A3B-Thinking-250730BQwen (Alibaba) · 18 Läufe MPhi-3.5-mini-instruct3.8Bmicrosoft · 3 Läufe MQwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) · 22 Läufe MQwen3-14B14BQwen (Alibaba) · 6 Läufe Mgemma-3n-E4B-it8BGoogle · 6 Läufe MNVIDIA-Nemotron-3-Nano-30B-A3B30BNVIDIA · 3 Läufe MNemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA · 3 Läufe MNemotron-Cascade-2-30B-A3B30BNVIDIA · 3 Läufe Mgpt-oss-120b120BOpenAI · 6 Läufe MHuihui-Qwen3-VL-30B-A3B-Instruct-abliterated30BQwen (Alibaba) · 3 Läufe MLing-3.0-flash127.5BinclusionAI · 37 Läufe MMuse-Glimmer-30B29.8Bmeta-models · 3 Läufe MQwen2.5-32B-Instruct32.8BQwen (Alibaba) · 15 Läufe MQwen2.5-Coder-32B-Instruct32BQwen (Alibaba) · 21 Läufe MMagistral-Small-250924BMistral AI · 21 Läufe MDevstral-Small-250724BMistral AI · 23 Läufe MDevstral-Small-2-24B-Instruct-251224BMistral AI · 24 Läufe Mglm-4.7-flash31.2BZ.ai (Zhipu) · 3 Läufe MMistral-Small-3.1-24B-Instruct-250324BMistral AI · 22 Läufe MCodestral-22B-v0.122BMistral AI · 30 Läufe MQwen3.6-27B27BQwen (Alibaba) · 10 Läufe MQwen3-Coder-Next79.7BQwen (Alibaba) · 3 Läufe Mgemma-4-31B-it31BGoogle · 6 Läufe MGLM-4.5-Air106BZ.ai (Zhipu) · 12 Läufe MQwen3.5-122B-A10B122BQwen (Alibaba) · 17 Läufe MSeed-OSS-36B-Instruct36BByteDance Seed · 12 Läufe MLlama-3_3-Nemotron-Super-49B-v1_549BNVIDIA · 6 Läufe MMistral-Small-4-119B-2603119BMistral AI · 3 Läufe MOpenReasoning-Nemotron-32B32BNVIDIA · 3 Läufe MLaguna-S-2.1117.6BPoolside · 3 Läufe MQwen3.8-Flash-Next180BQwen (Alibaba) · 9 Läufe MNVIDIA-Nemotron-3-Super-120B-A12B120BNVIDIA · 6 Läufe MMiniMax-M2.5230BMiniMax · 18 Läufe MNemotron-H-47B-Reasoning-128K47BNVIDIA · 3 Läufe Mminimax-m2230BMiniMax · 3 Läufe MStep-3.5-Flash199.4BStepFun · 3 Läufe MDeepSeek-V4-Flash-284B-A13B284BDeepSeek · 3 Läufe MLaguna-M.1225.8BPoolside · 12 Läufe Mcommand-a-reasoning-08-2025111BCohere · 3 Läufe MQwen2.5-72B-Instruct72BQwen (Alibaba) · 3 Läufe MDevstral-2-123B-Instruct-2512123BMistral AI · 3 Läufe MMistral-Medium-3.5-128B128BMistral AI · 3 Läufe MLlama-3_1-Nemotron-Ultra-253B-v1253BNVIDIA · 3 Läufe
Throughput & latency

Performancebenchmark

80 veroeffentlichte Performance-Läufe auf ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI.

In the leaderboard →
Metric:
Size
GPUs
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.743,96 tok/s TG
Prefill 13.641 · TTFT 5.790 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
2gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.743,14 tok/s TG
Prefill 12.148 · TTFT 5.881 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
3gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.608,46 tok/s TG
Prefill 31.452 · TTFT 1.633 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclawDetails →
4gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.210,29 tok/s TG
Prefill 9.745 · TTFT 8.399 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
5NVIDIA-Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.196,98 tok/s TG
Prefill 6.074 · TTFT 10.280 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
6gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.082,39 tok/s TG
Prefill 6.941 · TTFT 9.659 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
7gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.022,79 tok/s TG
Prefill 18.744 · TTFT 2.204 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclawDetails →
8Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.009,04 tok/s TG
Prefill 4.090 · TTFT 12.734 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawUD-Q4_K_XLDetails →
9gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
973,54 tok/s TG
Prefill 23.599 · TTFT 460 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclawDetails →
10gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
971,35 tok/s TG
Prefill 9.983 · TTFT 2.015 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
11gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
969,62 tok/s TG
Prefill 12.437 · TTFT 1.852 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
12Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
913,39 tok/s TG
Prefill 8.119 · TTFT 11.247 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
13Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
883,39 tok/s TG
Prefill 5.377 · TTFT 12.467 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
14Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
717,61 tok/s TG
Prefill 52.503 · TTFT 1.022 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
15gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
710,36 tok/s TG
Prefill 8.954 · TTFT 2.695 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
16gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
702,86 tok/s TG
Prefill 5.157 · TTFT 6.385 ms
10×AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0Details →
17Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
696,81 tok/s TG
Prefill 41.362 · TTFT 722 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
18gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
677,50 tok/s TG
Prefill 2.978 · TTFT 18.549 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawUD-Q4_K_XLDetails →
19NVIDIA-Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
676,42 tok/s TG
Prefill 5.367 · TTFT 3.579 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
20gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
616,01 tok/s TG
Prefill 13.778 · TTFT 803 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclawDetails →
21gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
592,13 tok/s TG
Prefill 5.662 · TTFT 3.385 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
22Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
590,01 tok/s TG
Prefill 5.490 · TTFT 17.999 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
23Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
585,92 tok/s TG
Prefill 3.535 · TTFT 4.487 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawUD-Q4_K_XLDetails →
24SmolLM2-1.7B-Instruct1.7BHuggingFaceTB Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
531,74 tok/s TG
Prefill 44.141 · TTFT 1.002 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
25gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
505,77 tok/s TG
Prefill 5.745 · TTFT 7.265 ms
10×AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ4_K_MDetails →
26Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
497,64 tok/s TG
Prefill 8.340 · TTFT 5.360 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclawAWQDetails →
27Qwen3-0.6B0.6BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
495,51 tok/s TG
Prefill 19.609 · TTFT 628 ms
5×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ8_0Details →
28Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
489,71 tok/s TG
Prefill 8.631 · TTFT 3.252 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
29gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
486,20 tok/s TG
Prefill 4.345 · TTFT 5.863 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclawDetails →
30Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
479,20 tok/s TG
Prefill 40.760 · TTFT 356 ms
5×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
31Laguna-XS-2.133.4BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
468,61 tok/s TG
Prefill 4.836 · TTFT 11.175 ms
10×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
32Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
468,02 tok/s TG
Prefill 4.949 · TTFT 4.084 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
33Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
465,73 tok/s TG
Prefill 23.398 · TTFT 1.915 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
34gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
465,47 tok/s TG
Prefill 8.435 · TTFT 2.408 ms
10×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ8_0Details →
35gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
455,35 tok/s TG
Prefill 8.245 · TTFT 2.462 ms
10×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
36Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
451,00 tok/s TG
Prefill 3.878 · TTFT 14.664 ms
10×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
37Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
450,54 tok/s TG
Prefill 3.632 · TTFT 14.999 ms
10×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
38Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
447,00 tok/s TG
Prefill 3.645 · TTFT 15.139 ms
10×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
39Qwen3-1.7B1.7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
445,18 tok/s TG
Prefill 19.926 · TTFT 1.357 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
40Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
443,74 tok/s TG
Prefill 31.085 · TTFT 445 ms
5×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
41Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
442,02 tok/s TG
Prefill 16.333 · TTFT 3.286 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
42Llama-3.1-Nemotron-Nano-4B-v1.14.5BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
419,38 tok/s TG
Prefill 11.768 · TTFT 2.673 ms
10×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
43Llama-3.1-Nemotron-Nano-4B-v1.14.5BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
418,31 tok/s TG
Prefill 11.855 · TTFT 2.651 ms
10×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ8_0Details →
44Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
404,99 tok/s TG
Prefill 14.538 · TTFT 2.823 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
45Qwen3-1.7B1.7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
387,65 tok/s TG
Prefill 32.764 · TTFT 2.280 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
46Qwen3-0.6B0.6BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
384,19 tok/s TG
Prefill 49.306 · TTFT 1.939 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
47gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
360,92 tok/s TG
Prefill 2.636 · TTFT 6.319 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawUD-Q4_K_XLDetails →
48Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
360,12 tok/s TG
Prefill 19.755 · TTFT 1.579 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
49Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
358,15 tok/s TG
Prefill 19.410 · TTFT 1.565 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
50gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
357,72 tok/s TG
Prefill 4.799 · TTFT 4.228 ms
10×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ8_0Details →
51Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
355,86 tok/s TG
Prefill 24.866 · TTFT 2.634 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
52gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
347,49 tok/s TG
Prefill 4.656 · TTFT 4.348 ms
10×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
53gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
344,13 tok/s TG
Prefill 3.766 · TTFT 5.354 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0Details →
54gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
343,93 tok/s TG
Prefill 2.544 · TTFT 7.919 ms
10×AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
55SmolLM2-1.7B-Instruct1.7BHuggingFaceTB Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
338,72 tok/s TG
Prefill 33.135 · TTFT 574 ms
5×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
56gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
331,51 tok/s TG
Prefill 6.908 · TTFT 1.433 ms
5×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
57gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
329,94 tok/s TG
Prefill 3.647 · TTFT 5.519 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
58Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
326,73 tok/s TG
Prefill 13.426 · TTFT 1.202 ms
5×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
59Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
324,87 tok/s TG
Prefill 7.451 · TTFT 4.042 ms
10×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
60gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
323,15 tok/s TG
Prefill 3.285 · TTFT 3.021 ms
5×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
61Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
323,12 tok/s TG
Prefill 5.337 · TTFT 5.911 ms
10×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0Details →
62gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
322,89 tok/s TG
Prefill 27.208 · TTFT 972 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
63Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
322,77 tok/s TG
Prefill 5.717 · TTFT 5.160 ms
10×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ4_K_MDetails →
64Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
321,67 tok/s TG
Prefill 7.148 · TTFT 4.460 ms
10×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
65Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
320,40 tok/s TG
Prefill 19.188 · TTFT 3.026 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
66gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
319,92 tok/s TG
Prefill 3.167 · TTFT 3.125 ms
5×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0Details →
67Laguna-XS-2.133.4BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
319,02 tok/s TG
Prefill 1.498 · TTFT 42.331 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
68Laguna-XS-2.133.4BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
318,94 tok/s TG
Prefill 1.446 · TTFT 42.781 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
69Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
318,66 tok/s TG
Prefill 5.742 · TTFT 2.122 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclawAWQDetails →
70Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
318,54 tok/s TG
Prefill 19.091 · TTFT 830 ms
5×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
71Laguna-XS-2.133.4BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
318,47 tok/s TG
Prefill 1.427 · TTFT 42.816 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
72Llama-3.1-Nemotron-Nano-4B-v1.14.5BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
318,18 tok/s TG
Prefill 9.348 · TTFT 1.524 ms
5×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
73Laguna-XS-2.133.4BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
318,17 tok/s TG
Prefill 1.479 · TTFT 42.546 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
74gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
316,40 tok/s TG
Prefill 7.121 · TTFT 1.391 ms
5×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ8_0Details →
75Laguna-XS-2.133.4BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
316,35 tok/s TG
Prefill 1.470 · TTFT 42.801 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
76Laguna-XS-2.133.4BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
316,28 tok/s TG
Prefill 1.496 · TTFT 42.551 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_MDetails →
77gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
315,66 tok/s TG
Prefill 3.728 · TTFT 2.722 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclawDetails →
78Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
315,53 tok/s TG
Prefill 2.703 · TTFT 7.505 ms
10×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
79Qwen3-8B8.2BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
315,16 tok/s TG
Prefill 13.007 · TTFT 3.960 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
80gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
314,82 tok/s TG
Prefill 4.224 · TTFT 2.350 ms
5×AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ8_0Details →
Agent & chat rating

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI.

In the leaderboard →
Noch keine Harnessbenchmarks auf diesem Mainboard.

← All hardware