Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
🧠
Processor

AMD Ryzen Threadripper PRO 5975WX 32-Cores

AMD
606Benchmarks
53Models
606Performance
0Harness
Best generation
1.744,0 tok/s
gemma-4-E2B-it
∅ Generation
134,2 tok/s
Schnitt aus 606 Läufen
Best prefill
31.452 tok/s
Prompt processing
Best TTFT
179 ms
Time to First Token
Best harness rate
%
noch kein Harness
🏆
gemma-4-E2B-it läuft am schnellsten auf dieser CPU · 1.744,0 tok/s
Bester Prefill: 31.452 tok/s · 53 Modelle getestet

Top models

Bester gemessener Durchsatz je Modell auf AMD Ryzen Threadripper PRO 5975WX 32-Cores – umschaltbar nach Generation, Prefill oder Kombiwert.

gemma-4-E2B-it5B
1.744,0 tok/s
gpt-oss-20b20B
1.210,3 tok/s
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
Ornith-1.0-9B9B
883,4 tok/s
gemma-4-12B-it12B
677,5 tok/s
Laguna-XS-2.1
319,0 tok/s
Performance profile

Durchsatz auf AMD Ryzen Threadripper PRO 5975WX 32-Cores

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

MODnach Modell

2.2181.6641.1095550,005.04310.08615.130Prefill (tok/s)Generation (tok/s)gemma-4-E2B-it - 1.744,0 tok/s Generation, 12.315 tok/s Prefill, TTFT 3.210 ms (11 Laufe)gemma-4-E2B-itgpt-oss-20b - 1.210,3 tok/s Generation, 4.695 tok/s Prefill, TTFT 4.347 ms (11 Laufe)gpt-oss-20bNemotron-3-Nano-4B - 1.197,0 tok/s Generation, 4.606 tok/s Prefill, TTFT 4.936 ms (3 Laufe)Nemotron-3-Nano-4Bgemma-4-E4B-it - 1.082,4 tok/s Generation, 11.281 tok/s Prefill, TTFT 4.013 ms (4 Laufe)gemma-4-E4B-itGemma-4-26B-A4B-it - 1.009,0 tok/s Generation, 3.368 tok/s Prefill, TTFT 7.693 ms (4 Laufe)Gemma-4-26B-A4B-itMeta-Llama-3.1-8B-Instruct - 913,4 tok/s Generation, 7.255 tok/s Prefill, TTFT 6.021 ms (5 Laufe)Meta-Llama-3.1-8B-Ins...Ornith-1.0-9B - 883,4 tok/s Generation, 3.636 tok/s Prefill, TTFT 8.108 ms (5 Laufe)Ornith-1.0-9Bgemma-4-12B-it - 677,5 tok/s Generation, 3.422 tok/s Prefill, TTFT 8.363 ms (4 Laufe)gemma-4-12B-itMinistral-3-14B-Reasoning-2512 - 590,0 tok/s Generation, 4.563 tok/s Prefill, TTFT 9.746 ms (6 Laufe)Ministral-3-14B-Reaso...Laguna-XS-2.1 - 319,0 tok/s Generation, 1.469 tok/s Prefill, TTFT 42.637 ms (6 Laufe)Laguna-XS-2.1Ornith-1.0-35B - 309,0 tok/s Generation, 1.120 tok/s Prefill, TTFT 42.243 ms (1 Lauf)Ornith-1.0-35BQwen3.6-35B-A3B - 296,2 tok/s Generation, 3.206 tok/s Prefill, TTFT 15.298 ms (3 Laufe)Qwen3.6-35B-A3BQwen3-Coder-30B-A3B-Instruct - 289,5 tok/s Generation, 7.349 tok/s Prefill, TTFT 4.926 ms (5 Laufe)Qwen3-Coder-30B-A3B-I...North-Mini-Code-1.0 - 276,9 tok/s Generation, 3.500 tok/s Prefill, TTFT 5.729 ms (1 Lauf)North-Mini-Code-1.0Qwen3-30B-A3B-Instruct-2507 - 267,7 tok/s Generation, 6.028 tok/s Prefill, TTFT 5.461 ms (4 Laufe)Qwen3-30B-A3B-Instruc...Nemotron-3-Nano-30B-A3B - 263,3 tok/s Generation, 784 tok/s Prefill, TTFT 55.800 ms (1 Lauf)Nemotron-3-Nano-30B-A...Nemotron-3-Nano-Omni-30B-A3B-Reasoning - 262,5 tok/s Generation, 811 tok/s Prefill, TTFT 55.388 ms (1 Lauf)Nemotron-3-Nano-Omni-...Nemotron-Cascade-2-30B-A3B - 262,4 tok/s Generation, 822 tok/s Prefill, TTFT 55.319 ms (1 Lauf)Nemotron-Cascade-2-30...Qwen3-30B-A3B-Thinking-2507 - 258,3 tok/s Generation, 6.602 tok/s Prefill, TTFT 4.863 ms (3 Laufe)Qwen3-30B-A3B-Thinkin...Qwen3-VL-30B-A3B-Instruct - 245,1 tok/s Generation, 5.881 tok/s Prefill, TTFT 4.862 ms (1 Lauf)Qwen3-VL-30B-A3B-Inst...
gemma-4-E2B-it 1.744,0 tok/sgpt-oss-20b 1.210,3 tok/sNemotron-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/sgemma-4-12B-it 677,5 tok/sMinistral-3-14B-Reasoning-2512 590,0 tok/sLaguna-XS-2.1 319,0 tok/sOrnith-1.0-35B 309,0 tok/sQwen3.6-35B-A3B 296,2 tok/sQwen3-Coder-30B-A3B-Instruct 289,5 tok/sNorth-Mini-Code-1.0 276,9 tok/sQwen3-30B-A3B-Instruct-2507 267,7 tok/sNemotron-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/sQwen3-30B-A3B-Thinking-2507 258,3 tok/sQwen3-VL-30B-A3B-Instruct 245,1 tok/s

ENGnach Engine

1.9451.8111.6761.5421.4072.5656.79111.01715.243Prefill (tok/s)Generation (tok/s)llama.cpp - 1.744,0 tok/s Generation, 4.816 tok/s Prefill, TTFT 12.286 ms (70 Laufe)llama.cppvLLM - 1.608,5 tok/s Generation, 12.992 tok/s Prefill, TTFT 2.941 ms (10 Laufe)vLLM
llama.cpp 1.744,0 tok/svLLM 1.608,5 tok/s

GPUnach Grafikkarte

2.1981.6491.0995500,03.8155.1136.4117.709Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 5070 Ti - 1.744,0 tok/s Generation, 6.889 tok/s Prefill, TTFT 15.548 ms (41 Laufe)NVIDIA GeForce RTX 50...AMD Radeon PRO W7800 48GB - 702,9 tok/s Generation, 4.818 tok/s Prefill, TTFT 6.560 ms (21 Laufe)AMD Radeon PRO W7800 ...AMD Radeon PRO W7900 Dual Slot - 344,1 tok/s Generation, 4.634 tok/s Prefill, TTFT 6.346 ms (18 Laufe)AMD Radeon PRO W7900 ...
NVIDIA GeForce RTX 5070 Ti 1.744,0 tok/sAMD Radeon PRO W7800 48GB 702,9 tok/sAMD Radeon PRO W7900 Dual Slot 344,1 tok/s
Platform

Mainboards with this CPU

Auf diesen Boards wurde AMD Ryzen Threadripper PRO 5975WX 32-Cores gemessen – anklicken für Board-Details mit CPUs und Modellen.

Throughput & latency

Performancebenchmark

80 veroeffentlichte Performance-Läufe auf AMD Ryzen Threadripper PRO 5975WX 32-Cores.

In the leaderboard →
Metric:
Size
#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_M
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_M
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 RAMvLLMgodclaw
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_M
5Nemotron-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_M
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_M
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 RAMvLLMgodclaw
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_XL
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 RAMvLLMgodclaw
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_M
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_M
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_M
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_M
14gpt-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_M
15gemma-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_0
16gemma-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_XL
17Nemotron-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_M
18gemma-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 RAMvLLMgodclaw
19gemma-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_M
20Ministral-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_M
21Gemma-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_XL
22gemma-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_M
23Ministral-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 RAMvLLMgodclawAWQ
24Meta-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_M
25gemma-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 RAMvLLMgodclaw
26Ornith-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_M
27gemma-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_XL
28gpt-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_0
29gpt-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_M
30gpt-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_M
31gpt-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_M
32Meta-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_0
33Meta-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_M
34gpt-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_0
35Laguna-XS-2.1Poolside 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_M
36Laguna-XS-2.1Poolside 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_M
37Ministral-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 RAMvLLMgodclawAWQ
38Laguna-XS-2.1Poolside 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_M
39Laguna-XS-2.1Poolside 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_M
40Laguna-XS-2.1Poolside 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_M
41Laguna-XS-2.1Poolside 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_M
42gemma-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 RAMvLLMgodclaw
43Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
312,21 tok/s TG
Prefill 5.010 · TTFT 5.594 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
44Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
309,02 tok/s TG
Prefill 1.120 · TTFT 42.243 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
45gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
306,90 tok/s TG
Prefill 2.293 · TTFT 4.306 ms
5×AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
46Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
296,15 tok/s TG
Prefill 4.336 · TTFT 4.376 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
47Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
293,98 tok/s TG
Prefill 2.069 · TTFT 9.136 ms
10×AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0
48Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
289,48 tok/s TG
Prefill 11.717 · TTFT 3.710 ms
10×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMvLLMgodclawAWQ
49gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
279,96 tok/s TG
Prefill 4.128 · TTFT 2.405 ms
5×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0
50Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
279,88 tok/s TG
Prefill 6.465 · TTFT 4.568 ms
10×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0
51Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
276,95 tok/s TG
Prefill 7.786 · TTFT 4.143 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
52North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
276,90 tok/s TG
Prefill 3.500 · TTFT 5.729 ms
10×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0
53gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
276,28 tok/s TG
Prefill 9.272 · TTFT 213 ms
1×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
54Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
272,78 tok/s TG
Prefill 1.270 · TTFT 14.950 ms
10×AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0
55Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
271,15 tok/s TG
Prefill 1.523 · TTFT 12.453 ms
10×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0
56Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
267,70 tok/s TG
Prefill 6.847 · TTFT 4.383 ms
10×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0
57Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
264,15 tok/s TG
Prefill 7.432 · TTFT 4.406 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
58gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
263,50 tok/s TG
Prefill 3.150 · TTFT 4.792 ms
10×AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0
59Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
263,34 tok/s TG
Prefill 784 · TTFT 55.800 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
60Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
262,93 tok/s TG
Prefill 8.472 · TTFT 4.535 ms
10×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMvLLMgodclawAWQ
61Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
262,45 tok/s TG
Prefill 811 · TTFT 55.388 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
62Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
262,44 tok/s TG
Prefill 822 · TTFT 55.319 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
63Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
258,36 tok/s TG
Prefill 5.960 · TTFT 5.584 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0
64Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
258,25 tok/s TG
Prefill 6.921 · TTFT 4.438 ms
10×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0
65Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
257,54 tok/s TG
Prefill 4.819 · TTFT 6.626 ms
10×AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
66Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
254,59 tok/s TG
Prefill 7.497 · TTFT 4.296 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
67gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
253,35 tok/s TG
Prefill 5.135 · TTFT 1.933 ms
5×AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0
68Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
251,08 tok/s TG
Prefill 5.146 · TTFT 6.222 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0
69Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
247,30 tok/s TG
Prefill 3.039 · TTFT 6.513 ms
10×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ4_K_M
70Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
246,82 tok/s TG
Prefill 4.686 · TTFT 6.831 ms
10×AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
71Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
245,10 tok/s TG
Prefill 5.881 · TTFT 4.862 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
72Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
244,12 tok/s TG
Prefill 2.809 · TTFT 7.040 ms
10×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0
73Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
243,46 tok/s TG
Prefill 2.311 · TTFT 25.408 ms
10×AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawUD-Q4_K_M
74gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
242,32 tok/s TG
Prefill 6.971 · TTFT 284 ms
1×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
75Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
241,10 tok/s TG
Prefill 5.388 · TTFT 5.855 ms
10×2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ8_0
76Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
239,26 tok/s TG
Prefill 2.309 · TTFT 8.469 ms
10×2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ8_0
77gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
238,53 tok/s TG
Prefill 6.897 · TTFT 1.885 ms
5×AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ4_K_M
78Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
235,51 tok/s TG
Prefill 2.971 · TTFT 16.110 ms
10×AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAMllama.cppgodclawQ4_K_M
79Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
235,12 tok/s TG
Prefill 3.475 · TTFT 6.384 ms
10×AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
80Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
233,69 tok/s TG
Prefill 2.376 · TTFT 950 ms
1×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawQ4_K_M
Agent & chat rating

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf AMD Ryzen Threadripper PRO 5975WX 32-Cores.

In the leaderboard →
Noch keine Harnessbenchmarks auf dieser Hardware.

← All hardware

Technische Daten

Technische Daten – AMD Ryzen Threadripper PRO 5975WX 32-Cores

HerstellerAMD
Best generation1.744,0 tok/s
Best prefill31.452 tok/s
Models53
Messläufe (Performance)606