Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Anmelden Registrieren
Beta
🎮
Grafikkarte

NVIDIA RTX A6000

NVIDIA45 GB VRAM
27Benchmarks
8Modelle
27Performance
0Harness
Beste Generation
668,0 tok/s
gemma-4-E2B-it
∅ Generation
239,5 tok/s
Schnitt aus 27 Läufen
Bester Prefill
11.047 tok/s
Prompt-Verarbeitung
Bester TTFT
236 ms
Time to First Token
Beste Harness-Quote
–%
noch kein Harness
🏆
gemma-4-E2B-it läuft am schnellsten auf dieser GPU · 668,0 tok/s
Bester Prefill: 11.047 tok/s · 8 Modelle getestet

Top-Modelle

Bester gemessener Durchsatz je Modell auf NVIDIA RTX A6000 – umschaltbar nach Generation, Prefill oder Kombiwert.

gemma-4-E2B-it5B
668,0 tok/s
gpt-oss-20b20B
378,5 tok/s
Qwen3-Coder-30B-A3B-Instruct30B
344,4 tok/s
Qwen3-30B-A3B-Instruct-250730B
339,7 tok/s
Qwen3.6-35B-A3B35B
286,7 tok/s
Nemotron-3-Nano-4B4B
277,4 tok/s
Nemotron-Cascade-2-30B-A3B30B
250,3 tok/s
Mistral-Small-3.1-24B-Instruct-250324B
159,9 tok/s
Anzeige
Performanceprofil

Durchsatz auf NVIDIA RTX A6000

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

MODnach Modell

8366274182090,06304.4318.23212.033Prefill (tok/s)Generation (tok/s)gemma-4-E2B-it - 668,0 tok/s Generation, 10.079 tok/s Prefill, TTFT 985 ms (3 Laufe)gemma-4-E2B-itgpt-oss-20b - 378,5 tok/s Generation, 6.302 tok/s Prefill, TTFT 1.592 ms (3 Laufe)gpt-oss-20bQwen3-Coder-30B-A3B-Instruct - 344,4 tok/s Generation, 8.324 tok/s Prefill, TTFT 1.578 ms (3 Laufe)Qwen3-Coder-30B-A3B-I...Qwen3-30B-A3B-Instruct-2507 - 339,7 tok/s Generation, 8.303 tok/s Prefill, TTFT 1.567 ms (3 Laufe)Qwen3-30B-A3B-Instruc...Qwen3.6-35B-A3B - 286,7 tok/s Generation, 4.159 tok/s Prefill, TTFT 2.368 ms (3 Laufe)Qwen3.6-35B-A3BNemotron-3-Nano-4B - 277,4 tok/s Generation, 4.886 tok/s Prefill, TTFT 2.183 ms (6 Laufe)Nemotron-3-Nano-4BNemotron-Cascade-2-30B-A3B - 250,3 tok/s Generation, 4.976 tok/s Prefill, TTFT 2.184 ms (3 Laufe)Nemotron-Cascade-2-30...Mistral-Small-3.1-24B-Instruct-2503 - 159,9 tok/s Generation, 2.583 tok/s Prefill, TTFT 4.703 ms (3 Laufe)Mistral-Small-3.1-24B...
gemma-4-E2B-it 668,0 tok/sgpt-oss-20b 378,5 tok/sQwen3-Coder-30B-A3B-Instruct 344,4 tok/sQwen3-30B-A3B-Instruct-2507 339,7 tok/sQwen3.6-35B-A3B 286,7 tok/sNemotron-3-Nano-4B 277,4 tok/sNemotron-Cascade-2-30B-A3B 250,3 tok/sMistral-Small-3.1-24B-Instruct-2503 159,9 tok/s

ENGnach Engine

7357016686356015.6925.9346.1766.419Prefill (tok/s)Generation (tok/s)llama.cpp - 668,0 tok/s Generation, 6.055 tok/s Prefill, TTFT 2.149 ms (27 Laufe)llama.cpp
llama.cpp 668,0 tok/s

CPUnach Prozessor

7357016686356015.6925.9346.1766.419Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 668,0 tok/s Generation, 6.055 tok/s Prefill, TTFT 2.149 ms (27 Laufe)AMD Ryzen Threadrippe...
AMD Ryzen Threadripper PRO 7955WX 16-Cores 668,0 tok/s
Durchsatz & Latenz

Performancebenchmark

27 veroeffentlichte Performance-Läufe auf NVIDIA RTX A6000.

Im Leaderboard →
Messwert:
Größe
#Modell / HerstellerMesswerteParallelGPU / CPU / RAMRuntime
1gemma-4-E2B-it5BQ4_K_MGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i
668,00 tok/s TG
Prefill 11.047 · TTFT 1.802 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
2gemma-4-E2B-it5BQ4_K_MGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i
462,78 tok/s TG
Prefill 10.812 · TTFT 917 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
3gpt-oss-20b20BMXFP4OpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
378,51 tok/s TG
Prefill 6.766 · TTFT 2.939 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
4Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
344,35 tok/s TG
Prefill 10.942 · TTFT 2.759 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
5Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
339,73 tok/s TG
Prefill 10.614 · TTFT 2.771 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
6Qwen3.6-35B-A3B35BQ4_K_MQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
286,68 tok/s TG
Prefill 4.535 · TTFT 4.311 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
7Nemotron-3-Nano-4B4BQ4_K_MNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i
277,39 tok/s TG
Prefill 5.993 · TTFT 3.672 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
8gpt-oss-20b20BMXFP4OpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
273,57 tok/s TG
Prefill 6.722 · TTFT 1.473 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
9Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
266,26 tok/s TG
Prefill 8.447 · TTFT 1.538 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
10Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
260,37 tok/s TG
Prefill 8.681 · TTFT 1.498 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
11Nemotron-Cascade-2-30B-A3B30BQ4_K_MNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
250,32 tok/s TG
Prefill 5.865 · TTFT 3.782 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
12Nemotron-3-Nano-4B4BQ4_K_MNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i
248,17 tok/s TG
Prefill 4.462 · TTFT 2.412 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
13Qwen3.6-35B-A3B35BQ4_K_MQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
239,95 tok/s TG
Prefill 4.270 · TTFT 2.268 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
14Nemotron-Cascade-2-30B-A3B30BQ4_K_MNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
219,79 tok/s TG
Prefill 4.791 · TTFT 2.262 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
15Nemotron-3-Nano-4B4BQ8_0NVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i
208,19 tok/s TG
Prefill 6.153 · TTFT 3.583 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
16gemma-4-E2B-it5BQ4_K_MGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i
194,48 tok/s TG
Prefill 8.378 · TTFT 236 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
17Nemotron-3-Nano-4B4BQ8_0NVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i
187,29 tok/s TG
Prefill 4.534 · TTFT 2.375 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
18Nemotron-3-Nano-4B4BQ4_K_MNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i
166,48 tok/s TG
Prefill 4.080 · TTFT 529 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
19gpt-oss-20b20BMXFP4OpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
165,76 tok/s TG
Prefill 5.419 · TTFT 365 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
20Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
161,57 tok/s TG
Prefill 5.583 · TTFT 437 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
21Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
160,98 tok/s TG
Prefill 5.616 · TTFT 434 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
22Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
159,85 tok/s TG
Prefill 3.304 · TTFT 8.318 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
23Nemotron-Cascade-2-30B-A3B30BQ4_K_MNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
157,01 tok/s TG
Prefill 4.273 · TTFT 508 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
24Qwen3.6-35B-A3B35BQ4_K_MQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
131,05 tok/s TG
Prefill 3.671 · TTFT 526 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
25Nemotron-3-Nano-4B4BQ8_0NVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i
124,60 tok/s TG
Prefill 4.092 · TTFT 528 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
26Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
94,61 tok/s TG
Prefill 2.657 · TTFT 4.592 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
27Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
38,44 tok/s TG
Prefill 1.790 · TTFT 1.199 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliDetails →
Agent- & Chat-Bewertung

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf NVIDIA RTX A6000.

Im Leaderboard →
Noch keine Harnessbenchmarks auf dieser Hardware.

← Alle Hardware

Technische Daten

Technische Daten – NVIDIA RTX A6000

HerstellerNVIDIA
VRAM45 GB
Beste Generation668,0 tok/s
Bester Prefill11.047 tok/s
Modelle8
Messläufe (Performance)27