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

NVIDIA Tesla P100 PCIe 16GB

NVIDIA16 GB VRAM
28Benchmarks
11Models
28Performance
0Harness
250 WMax power
Best generation
111,1 tok/s
gpt-oss-20b
∅ Generation
40,0 tok/s
Schnitt aus 28 Läufen
Best prefill
1.115 tok/s
Prompt processing
Best TTFT
2.613 ms
Time to First Token
Best harness rate
–%
noch kein Harness
🏆
gpt-oss-20b läuft am schnellsten auf dieser GPU · 111,1 tok/s
Bester Prefill: 1.115 tok/s · 11 Modelle getestet

Top models

Bester gemessener Durchsatz je Modell auf NVIDIA Tesla P100 PCIe 16GB – umschaltbar nach Generation, Prefill oder Kombiwert.

gpt-oss-20b20B
111,1 tok/s
gemma-4-E4B-it8B
97,1 tok/s
Meta-Llama-3.1-8B-Instruct8B
67,6 tok/s
Ornith-1.0-9B9B
64,5 tok/s
gemma-4-12B-it12B
45,8 tok/s
Ministral-3-14B-Reasoning-251214B
41,5 tok/s
Magistral-Small-250924B
24,7 tok/s
Mistral-Small-3.1-24B-Instruct-250324B
23,8 tok/s
Devstral-Small-2-24B-Instruct-251224B
23,3 tok/s
Devstral-Small-250724B
23,2 tok/s
Anzeige
Performance profile

Durchsatz auf NVIDIA Tesla P100 PCIe 16GB

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

MODnach Modell

14010570,035,00,0153566971.037Prefill (tok/s)Generation (tok/s)gpt-oss-20b - 111,1 tok/s Generation, 646 tok/s Prefill, TTFT 16.076 ms (3 Laufe)gpt-oss-20bgemma-4-E4B-it - 97,1 tok/s Generation, 778 tok/s Prefill, TTFT 13.485 ms (3 Laufe)gemma-4-E4B-itMeta-Llama-3.1-8B-Instruct - 67,6 tok/s Generation, 864 tok/s Prefill, TTFT 15.746 ms (3 Laufe)Meta-Llama-3.1-8B-Ins...Ornith-1.0-9B - 64,5 tok/s Generation, 638 tok/s Prefill, TTFT 16.496 ms (3 Laufe)Ornith-1.0-9Bgemma-4-12B-it - 45,8 tok/s Generation, 312 tok/s Prefill, TTFT 33.496 ms (3 Laufe)gemma-4-12B-itMinistral-3-14B-Reasoning-2512 - 41,5 tok/s Generation, 501 tok/s Prefill, TTFT 25.353 ms (3 Laufe)Ministral-3-14B-Reaso...Magistral-Small-2509 - 24,7 tok/s Generation, 189 tok/s Prefill, TTFT 35.758 ms (2 Laufe)Magistral-Small-2509Mistral-Small-3.1-24B-Instruct-2503 - 23,8 tok/s Generation, 218 tok/s Prefill, TTFT 30.869 ms (2 Laufe)Mistral-Small-3.1-24B...Devstral-Small-2-24B-Instruct-2512 - 23,3 tok/s Generation, 235 tok/s Prefill, TTFT 34.419 ms (2 Laufe)Devstral-Small-2-24B-...Devstral-Small-2507 - 23,2 tok/s Generation, 276 tok/s Prefill, TTFT 39.340 ms (2 Laufe)Devstral-Small-2507Codestral-22B-v0.1 - 22,2 tok/s Generation, 224 tok/s Prefill, TTFT 35.995 ms (2 Laufe)Codestral-22B-v0.1
gpt-oss-20b 111,1 tok/sgemma-4-E4B-it 97,1 tok/sMeta-Llama-3.1-8B-Instruct 67,6 tok/sOrnith-1.0-9B 64,5 tok/sgemma-4-12B-it 45,8 tok/sMinistral-3-14B-Reasoning-2512 41,5 tok/sMagistral-Small-2509 24,7 tok/sMistral-Small-3.1-24B-Instruct-2503 23,8 tok/sDevstral-Small-2-24B-Instruct-2512 23,3 tok/sDevstral-Small-2507 23,2 tok/sCodestral-22B-v0.1 22,2 tok/s

ENGnach Engine

122117111106100453472492511Prefill (tok/s)Generation (tok/s)llama.cpp - 111,1 tok/s Generation, 482 tok/s Prefill, TTFT 25.526 ms (28 Laufe)llama.cpp
llama.cpp 111,1 tok/s

CPUnach Prozessor

122117111106100453472492511Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 7945HX with Radeon Graphics - 111,1 tok/s Generation, 482 tok/s Prefill, TTFT 25.526 ms (28 Laufe)AMD Ryzen 9 7945HX wi...
AMD Ryzen 9 7945HX with Radeon Graphics 111,1 tok/s
Throughput & latency

Performancebenchmark

28 veroeffentlichte Performance-Läufe auf NVIDIA Tesla P100 PCIe 16GB.

In the leaderboard →
Metric:
Size
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
111,12 tok/s TG
Prefill 616 · TTFT 16.066 ms
5×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliMXFP4Details →
2gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
105,30 tok/s TG
Prefill 694 · TTFT 29.007 ms
10×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliMXFP4Details →
3gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
97,08 tok/s TG
Prefill 757 · TTFT 13.077 ms
5×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
4Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
67,58 tok/s TG
Prefill 888 · TTFT 15.224 ms
5×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
5Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
64,46 tok/s TG
Prefill 592 · TTFT 16.869 ms
5×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
6gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
63,18 tok/s TG
Prefill 627 · TTFT 3.155 ms
1×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliMXFP4Details →
7gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
58,96 tok/s TG
Prefill 818 · TTFT 24.766 ms
10×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
8gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
45,75 tok/s TG
Prefill 305 · TTFT 32.520 ms
5×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
9gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
43,23 tok/s TG
Prefill 758 · TTFT 2.613 ms
1×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
10Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
41,46 tok/s TG
Prefill 476 · TTFT 25.832 ms
5×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
11Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
37,65 tok/s TG
Prefill 776 · TTFT 29.085 ms
10×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
12Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
37,29 tok/s TG
Prefill 1.115 · TTFT 27.826 ms
10×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
13Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
35,46 tok/s TG
Prefill 589 · TTFT 4.189 ms
1×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
14Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
33,54 tok/s TG
Prefill 547 · TTFT 3.535 ms
1×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
15gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
25,04 tok/s TG
Prefill 333 · TTFT 61.247 ms
10×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
16Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
24,74 tok/s TG
Prefill 212 · TTFT 57.889 ms
5×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
17Mistral-Small-3.1-24B-Instruct-250324BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
23,84 tok/s TG
Prefill 277 · TTFT 48.247 ms
5×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
18Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
23,29 tok/s TG
Prefill 273 · TTFT 55.104 ms
5×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
19Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
23,15 tok/s TG
Prefill 308 · TTFT 64.768 ms
5×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
20Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
23,11 tok/s TG
Prefill 639 · TTFT 44.373 ms
10×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
21Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
22,41 tok/s TG
Prefill 388 · TTFT 5.855 ms
1×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
22gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
22,30 tok/s TG
Prefill 298 · TTFT 6.721 ms
1×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
23Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
22,24 tok/s TG
Prefill 263 · TTFT 57.267 ms
5×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
24Mistral-Small-3.1-24B-Instruct-250324BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
13,57 tok/s TG
Prefill 159 · TTFT 13.491 ms
1×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
25Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
13,55 tok/s TG
Prefill 166 · TTFT 13.627 ms
1×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
26Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
13,51 tok/s TG
Prefill 185 · TTFT 14.723 ms
1×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
27Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
13,47 tok/s TG
Prefill 197 · TTFT 13.734 ms
1×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
28Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
13,34 tok/s TG
Prefill 243 · TTFT 13.913 ms
1×NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
Agent & chat rating

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf NVIDIA Tesla P100 PCIe 16GB.

In the leaderboard →
Noch keine Harnessbenchmarks auf dieser Hardware.

← All hardware

Technische Daten

Technische Daten – NVIDIA Tesla P100 PCIe 16GB

HerstellerNVIDIA
ArchitekturPascal
VRAM16 GB
Speicherbandbreite732 GB/s
TDP250 W
PCIe3.0
Release06/2016
Best generation111,1 tok/s
Best prefill1.115 tok/s
Models11
Messläufe (Performance)28