Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
🎮
Graphics card

Tesla V100-PCIE-32GB

NVIDIA32 GB VRAM
30Benchmarks
7Models
30Performance
0Harness
Best generation
361,8 tok/s
gemma-4-E2B-it
∅ Generation
139,9 tok/s
Schnitt aus 30 Läufen
Best prefill
7.233 tok/s
Prompt processing
Best TTFT
378 ms
Time to First Token
Best harness rate
–%
noch kein Harness
🏆
gemma-4-E2B-it läuft am schnellsten auf dieser GPU · 361,8 tok/s
Bester Prefill: 7.233 tok/s · 7 Modelle getestet

Top models

Bester gemessener Durchsatz je Modell auf Tesla V100-PCIE-32GB – umschaltbar nach Generation, Prefill oder Kombiwert.

gemma-4-E2B-it5B
361,8 tok/s
Ornith-1.0-9B9B
248,7 tok/s
Qwen3.6-35B-A3B35B
225,9 tok/s
gpt-oss-20b20B
206,6 tok/s
gemma-4-12B-it12B
186,2 tok/s
Meta-Llama-3.1-8B-Instruct8B
122,6 tok/s
Ministral-3-14B-Reasoning-251214B
52,8 tok/s
Anzeige
Performance profile

Durchsatz auf Tesla V100-PCIE-32GB

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

MODnach Modell

4603452301150,002.3674.7347.101Prefill (tok/s)Generation (tok/s)gemma-4-E2B-it - 361,8 tok/s Generation, 5.868 tok/s Prefill, TTFT 1.823 ms (6 Laufe)gemma-4-E2B-itOrnith-1.0-9B - 248,7 tok/s Generation, 2.452 tok/s Prefill, TTFT 4.148 ms (6 Laufe)Ornith-1.0-9BQwen3.6-35B-A3B - 225,9 tok/s Generation, 975 tok/s Prefill, TTFT 8.633 ms (3 Laufe)Qwen3.6-35B-A3Bgpt-oss-20b - 206,6 tok/s Generation, 2.660 tok/s Prefill, TTFT 4.402 ms (3 Laufe)gpt-oss-20bgemma-4-12B-it - 186,2 tok/s Generation, 1.307 tok/s Prefill, TTFT 10.582 ms (6 Laufe)gemma-4-12B-itMeta-Llama-3.1-8B-Instruct - 122,6 tok/s Generation, 4.984 tok/s Prefill, TTFT 3.619 ms (3 Laufe)Meta-Llama-3.1-8B-Ins...Ministral-3-14B-Reasoning-2512 - 52,8 tok/s Generation, 1.847 tok/s Prefill, TTFT 9.122 ms (3 Laufe)Ministral-3-14B-Reaso...
gemma-4-E2B-it 361,8 tok/sOrnith-1.0-9B 248,7 tok/sQwen3.6-35B-A3B 225,9 tok/sgpt-oss-20b 206,6 tok/sgemma-4-12B-it 186,2 tok/sMeta-Llama-3.1-8B-Instruct 122,6 tok/sMinistral-3-14B-Reasoning-2512 52,8 tok/s

ENGnach Engine

3983803623443262.7942.9133.0323.150Prefill (tok/s)Generation (tok/s)llama.cpp - 361,8 tok/s Generation, 2.972 tok/s Prefill, TTFT 5.888 ms (30 Laufe)llama.cpp
llama.cpp 361,8 tok/s

CPUnach Prozessor

3983803623443262.7942.9133.0323.150Prefill (tok/s)Generation (tok/s)AMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics - 361,8 tok/s Generation, 2.972 tok/s Prefill, TTFT 5.888 ms (30 Laufe)AMD Ryzen 3 PRO 3200G...
AMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics 361,8 tok/s
Throughput & latency

Performancebenchmark

30 veroeffentlichte Performance-Läufe auf Tesla V100-PCIE-32GB.

In the leaderboard →
Metric:
Size
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
361,84 tok/s TG
Prefill 7.233 · TTFT 2.750 ms
10×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
2gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
353,85 tok/s TG
Prefill 4.758 · TTFT 4.353 ms
10×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ4_K_MDetails →
3gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
275,62 tok/s TG
Prefill 6.734 · TTFT 1.481 ms
5×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
4gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
255,41 tok/s TG
Prefill 6.332 · TTFT 1.575 ms
5×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ4_K_MDetails →
5Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
248,72 tok/s TG
Prefill 3.178 · TTFT 5.437 ms
10×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ4_K_MDetails →
6Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
225,93 tok/s TG
Prefill 1.021 · TTFT 8.456 ms
5×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ4_K_MDetails →
7Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
216,62 tok/s TG
Prefill 1.136 · TTFT 15.201 ms
10×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ4_K_MDetails →
8gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
206,60 tok/s TG
Prefill 3.450 · TTFT 2.889 ms
5×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
9Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
193,56 tok/s TG
Prefill 3.011 · TTFT 2.862 ms
5×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ4_K_MDetails →
10gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
186,18 tok/s TG
Prefill 1.748 · TTFT 10.113 ms
10×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ4_K_MDetails →
11gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
139,86 tok/s TG
Prefill 1.753 · TTFT 5.039 ms
5×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ4_K_MDetails →
12gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
138,88 tok/s TG
Prefill 2.354 · TTFT 9.328 ms
10×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
13gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
132,28 tok/s TG
Prefill 2.178 · TTFT 988 ms
1×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
14gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
128,96 tok/s TG
Prefill 4.924 · TTFT 402 ms
1×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ4_K_MDetails →
15Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
122,55 tok/s TG
Prefill 5.151 · TTFT 2.489 ms
5×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
16gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
117,98 tok/s TG
Prefill 5.227 · TTFT 378 ms
1×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
17Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
94,40 tok/s TG
Prefill 768 · TTFT 2.243 ms
1×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ4_K_MDetails →
18Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
93,40 tok/s TG
Prefill 3.060 · TTFT 3.167 ms
5×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
19Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
83,75 tok/s TG
Prefill 1.512 · TTFT 1.139 ms
1×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ4_K_MDetails →
20Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
83,10 tok/s TG
Prefill 6.957 · TTFT 7.450 ms
10×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
21Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
74,39 tok/s TG
Prefill 1.748 · TTFT 11.355 ms
10×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
22Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
69,93 tok/s TG
Prefill 2.843 · TTFT 920 ms
1×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
23Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
62,07 tok/s TG
Prefill 2.204 · TTFT 932 ms
1×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
24gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
58,59 tok/s TG
Prefill 1.147 · TTFT 1.541 ms
1×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ4_K_MDetails →
25Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
52,78 tok/s TG
Prefill 1.962 · TTFT 6.490 ms
5×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
26Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
52,41 tok/s TG
Prefill 1.260 · TTFT 19.903 ms
10×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
27gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
49,35 tok/s TG
Prefill 778 · TTFT 25.706 ms
10×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
28gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
47,87 tok/s TG
Prefill 1.491 · TTFT 7.113 ms
5×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
29gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
36,37 tok/s TG
Prefill 928 · TTFT 13.981 ms
1×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
30Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
35,13 tok/s TG
Prefill 2.320 · TTFT 975 ms
1×Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAMllama.cppgodclawQ8_0Details →
Agent & chat rating

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf Tesla V100-PCIE-32GB.

In the leaderboard →
Noch keine Harnessbenchmarks auf dieser Hardware.

← All hardware

Technische Daten

Technische Daten – Tesla V100-PCIE-32GB

HerstellerNVIDIA
VRAM32 GB
Best generation361,8 tok/s
Best prefill7.233 tok/s
Models7
Messläufe (Performance)30