Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
🎮
Graphics card

NVIDIA RTX A6000

NVIDIA45 GB VRAM
45Benchmarks
11Models
45Performance
0Harness
Best generation
668,0 tok/s
gemma-4-E2B-it
∅ Generation
245,1 tok/s
Schnitt aus 45 Läufen
Best prefill
11.197 tok/s
Prompt processing
Best TTFT
236 ms
Time to First Token
Best harness rate
%
noch kein Harness
🏆
gemma-4-E2B-it läuft am schnellsten auf dieser GPU · 668,0 tok/s
Bester Prefill: 11.197 tok/s · 11 Modelle getestet

Top models

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

gemma-4-E2B-it5B
668,0 tok/s
gemma-4-E4B-it8B
428,6 tok/s
gpt-oss-20b20B
378,5 tok/s
Ornith-1.0-9B9B
301,0 tok/s
Qwen3.6-35B-A3B35B
286,7 tok/s
Nemotron-3-Nano-4B4B
277,4 tok/s
Anzeige
Performance profile

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

8366274182090,06254.4368.24612.057Prefill (tok/s)Generation (tok/s)gemma-4-E2B-it - 668,0 tok/s Generation, 10.099 tok/s Prefill, TTFT 980 ms (6 Laufe)gemma-4-E2B-itgemma-4-E4B-it - 428,6 tok/s Generation, 6.063 tok/s Prefill, TTFT 1.652 ms (6 Laufe)gemma-4-E4B-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...Meta-Llama-3.1-8B-Instruct - 343,7 tok/s Generation, 7.328 tok/s Prefill, TTFT 1.837 ms (6 Laufe)Meta-Llama-3.1-8B-Ins...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...Ornith-1.0-9B - 301,0 tok/s Generation, 3.825 tok/s Prefill, TTFT 2.609 ms (3 Laufe)Ornith-1.0-9BQwen3.6-35B-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/sgemma-4-E4B-it 428,6 tok/sgpt-oss-20b 378,5 tok/sQwen3-Coder-30B-A3B-Instruct 344,4 tok/sMeta-Llama-3.1-8B-Instruct 343,7 tok/sQwen3-30B-A3B-Instruct-2507 339,7 tok/sOrnith-1.0-9B 301,0 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

7357016686356015.9676.2216.4756.729Prefill (tok/s)Generation (tok/s)llama.cpp - 668,0 tok/s Generation, 6.348 tok/s Prefill, TTFT 1.994 ms (45 Laufe)llama.cpp
llama.cpp 668,0 tok/s

CPUnach Prozessor

7357016686356015.9676.2216.4756.729Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 668,0 tok/s Generation, 6.348 tok/s Prefill, TTFT 1.994 ms (45 Laufe)AMD Ryzen Threadrippe...
AMD Ryzen Threadripper PRO 7955WX 16-Cores 668,0 tok/s
Throughput & latency

Performancebenchmark

45 veroeffentlichte Performance-Läufe auf NVIDIA RTX A6000.

In the leaderboard →
Metric:
Size
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1gemma-4-E2B-it5BQ4_K_MGoogle Performance benchmarkTimebench 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_cli
2gemma-4-E2B-it5BQ8_0Google Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
600,60 tok/s TG
Prefill 11.197 · TTFT 1.774 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
3gemma-4-E2B-it5BQ4_K_MGoogle Performance benchmarkTimebench 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_cli
4gemma-4-E2B-it5BQ8_0Google Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
429,79 tok/s TG
Prefill 10.850 · TTFT 916 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
5gemma-4-E4B-it8BQ4_K_MGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
428,56 tok/s TG
Prefill 6.452 · TTFT 3.073 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
6gpt-oss-20b20BMXFP4OpenAI Performance benchmarkTimebench 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_cli
7gemma-4-E4B-it8BQ8_0Google Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
375,94 tok/s TG
Prefill 6.660 · TTFT 2.979 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
8Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 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_cli
9Meta-Llama-3.1-8B-Instruct8BQ4_K_MMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
343,70 tok/s TG
Prefill 9.999 · TTFT 3.230 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
10Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 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_cli
11Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
300,99 tok/s TG
Prefill 4.071 · TTFT 4.790 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
12Qwen3.6-35B-A3B35BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 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_cli
13gemma-4-E4B-it8BQ4_K_MGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
283,39 tok/s TG
Prefill 6.346 · TTFT 1.565 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
14Nemotron-3-Nano-4B4BQ4_K_MNVIDIA Performance benchmarkTimebench 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_cli
15Meta-Llama-3.1-8B-Instruct8BQ8_0Meta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
276,49 tok/s TG
Prefill 9.874 · TTFT 3.124 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
16gpt-oss-20b20BMXFP4OpenAI Performance benchmarkTimebench 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_cli
17Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 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_cli
18Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 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_cli
19gemma-4-E4B-it8BQ8_0Google Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
254,04 tok/s TG
Prefill 6.450 · TTFT 1.538 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
20Nemotron-Cascade-2-30B-A3B30BQ4_K_MNVIDIA Performance benchmarkTimebench 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_cli
21Nemotron-3-Nano-4B4BQ4_K_MNVIDIA Performance benchmarkTimebench 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_cli
22Qwen3.6-35B-A3B35BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 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_cli
23Meta-Llama-3.1-8B-Instruct8BQ4_K_MMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
237,04 tok/s TG
Prefill 7.169 · TTFT 1.831 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
24Nemotron-Cascade-2-30B-A3B30BQ4_K_MNVIDIA Performance benchmarkTimebench 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_cli
25Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
209,92 tok/s TG
Prefill 3.882 · TTFT 2.491 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
26Nemotron-3-Nano-4B4BQ8_0NVIDIA Performance benchmarkTimebench 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_cli
27Meta-Llama-3.1-8B-Instruct8BQ8_0Meta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
197,34 tok/s TG
Prefill 6.940 · TTFT 1.849 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
28gemma-4-E2B-it5BQ4_K_MGoogle Performance benchmarkTimebench 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_cli
29Nemotron-3-Nano-4B4BQ8_0NVIDIA Performance benchmarkTimebench 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_cli
30Nemotron-3-Nano-4B4BQ4_K_MNVIDIA Performance benchmarkTimebench 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_cli
31gpt-oss-20b20BMXFP4OpenAI Performance benchmarkTimebench 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_cli
32Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 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_cli
33Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 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_cli
34Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI Performance benchmarkTimebench 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_cli
35Nemotron-Cascade-2-30B-A3B30BQ4_K_MNVIDIA Performance benchmarkTimebench 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_cli
36gemma-4-E2B-it5BQ8_0Google Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
153,69 tok/s TG
Prefill 8.308 · TTFT 239 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
37Qwen3.6-35B-A3B35BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 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_cli
38Nemotron-3-Nano-4B4BQ8_0NVIDIA Performance benchmarkTimebench 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_cli
39gemma-4-E4B-it8BQ4_K_MGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
119,55 tok/s TG
Prefill 5.239 · TTFT 378 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
40Meta-Llama-3.1-8B-Instruct8BQ4_K_MMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
102,47 tok/s TG
Prefill 4.866 · TTFT 508 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
41Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI Performance benchmarkTimebench 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_cli
42Ornith-1.0-9B9BQ4_K_MDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
93,36 tok/s TG
Prefill 3.523 · TTFT 547 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
43gemma-4-E4B-it8BQ8_0Google Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
87,28 tok/s TG
Prefill 5.229 · TTFT 378 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
44Meta-Llama-3.1-8B-Instruct8BQ8_0Meta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i
66,99 tok/s TG
Prefill 5.119 · TTFT 482 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli
45Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI Performance benchmarkTimebench 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_cli
Agent & chat rating

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf NVIDIA RTX A6000.

In the leaderboard →
Noch keine Harnessbenchmarks auf dieser Hardware.

← All hardware

Technische Daten

Technische Daten – NVIDIA RTX A6000

HerstellerNVIDIA
VRAM45 GB
Best generation668,0 tok/s
Best prefill11.197 tok/s
Models11
Messläufe (Performance)45