Created bymario-alka.dePowered bynoob2claw.detricoma.de
🎮
Grafikkarte

NVIDIA GeForce RTX 3090

NVIDIA24 GB VRAM
98Benchmarks
8Modelle
93LLM
4Bild
1Harness
350 WMax-Leistung
Beste Generation
3.484,3 tok/s
NVIDIA-Nemotron-3.5-Lightning-30B-A3B
∅ Generation
370,1 tok/s
Schnitt aus 93 Läufen
Bester Prefill
26.055 tok/s
Prompt-Verarbeitung
Bester TTFT
31 ms
Time to First Token
Beste Harness-Quote
80%
1 Harness-Läufe
🏆
NVIDIA-Nemotron-3.5-Lightning-30B-A3B läuft am schnellsten auf dieser GPU · 3.484,3 tok/s
Bester Prefill: 26.055 tok/s · 8 Modelle getestet

Top-Modelle

Bester gemessener Durchsatz je Modell auf NVIDIA GeForce RTX 3090 – umschaltbar nach Generation, Prefill oder Kombiwert.

NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6B
3.484,3 tok/s
Qwen3.8-Flash-Next180B
1.132,7 tok/s
Qwen3.6-35B-A3B35B
833,3 tok/s
gpt-oss-20b20B
448,2 tok/s
gpt-oss-120b120B
18,1 tok/s
Anzeige
Performanceprofil

Durchsatz auf NVIDIA GeForce RTX 3090

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

MODnach Modell

4.5123.3842.2561.1280,004.8429.68314.525Prefill (tok/s)Generation (tok/s)NVIDIA-Nemotron-3.5-Lightning-30B-A3B - 3.484,3 tok/s Generation, 11.447 tok/s Prefill, TTFT 3.078 ms (29 Laufe)NVIDIA-Nemotron-3.5-L...Qwen3.8-Flash-Next - 1.132,7 tok/s Generation, 2.117 tok/s Prefill, TTFT 29.438 ms (11 Laufe)Qwen3.8-Flash-NextQwen3.6-35B-A3B - 833,3 tok/s Generation, 6.588 tok/s Prefill, TTFT 3.818 ms (28 Laufe)Qwen3.6-35B-A3Bgpt-oss-20b - 448,2 tok/s Generation, 4.932 tok/s Prefill, TTFT 2.012 ms (3 Laufe)gpt-oss-20bMeta-Llama-3.1-8B-Instruct - 385,9 tok/s Generation, 12.021 tok/s Prefill, TTFT 1.982 ms (4 Laufe)Meta-Llama-3.1-8B-Ins...Qwen3-30B-A3B-Thinking-2507 - 371,7 tok/s Generation, 6.276 tok/s Prefill, TTFT 2.183 ms (3 Laufe)Qwen3-30B-A3B-Thinkin...Llama-3.1-Nemotron-Nano-4B-v1.1 - 86,3 tok/s Generation, 8.339 tok/s Prefill, TTFT 298 ms (1 Lauf)Llama-3.1-Nemotron-Na...
NVIDIA-Nemotron-3.5-Lightning-30B-A3B 3.484,3 tok/sQwen3.8-Flash-Next 1.132,7 tok/sQwen3.6-35B-A3B 833,3 tok/sgpt-oss-20b 448,2 tok/sMeta-Llama-3.1-8B-Instruct 385,9 tok/sQwen3-30B-A3B-Thinking-2507 371,7 tok/sLlama-3.1-Nemotron-Nano-4B-v1.1 86,3 tok/s

ENGnach Engine

4.4403.3302.2201.1100,005.72511.44917.174Prefill (tok/s)Generation (tok/s)tensorfold - 3.484,3 tok/s Generation, 12.218 tok/s Prefill, TTFT 3.184 ms (19 Laufe)tensorfoldstrata - 1.132,7 tok/s Generation, 2.687 tok/s Prefill, TTFT 23.939 ms (14 Laufe)strataunbekannt - 859,8 tok/s Generation, 14.240 tok/s Prefill, TTFT 715 ms (10 Laufe)unbekanntvLLM - 725,3 tok/s Generation, 6.888 tok/s Prefill, TTFT 3.780 ms (24 Laufe)vLLMllama.cpp - 448,2 tok/s Generation, 4.044 tok/s Prefill, TTFT 3.939 ms (12 Laufe)llama.cpp
tensorfold 3.484,3 tok/sstrata 1.132,7 tok/sunbekannt 859,8 tok/svLLM 725,3 tok/sllama.cpp 448,2 tok/s

CPUnach Prozessor

3.8333.6593.4843.3103.1367.4097.7248.0398.354Prefill (tok/s)Generation (tok/s)AMD Ryzen 5 5600X 6-Core Processor - 3.484,3 tok/s Generation, 7.882 tok/s Prefill, TTFT 6.845 ms (79 Laufe)AMD Ryzen 5 5600X 6-C...
AMD Ryzen 5 5600X 6-Core Processor 3.484,3 tok/s
Durchsatz & Latenz

Performancebenchmark

79 veroeffentlichte Performance-Läufe auf NVIDIA GeForce RTX 3090.

Im Leaderboard →
Messwert:
Größe
#Modell / HerstellerMesswerteParallelGPU / CPU / RAMRuntime
1NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3.484,32 tok/s TG
Prefill 8.256 · TTFT 14.388 ms
10×NVIDIA GeForce RTX 3090AMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclaw 1.1.6MLX 4-bit
2NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
2.867,15 tok/s TG
Prefill 8.107 · TTFT 17.054 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclaw 1.1.6MLX 4-bit
3NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.694,65 tok/s TG
Prefill 7.768 · TTFT 6.482 ms
5×NVIDIA GeForce RTX 3090AMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclaw 1.1.6MLX 4-bit
4NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.375,08 tok/s TG
Prefill 7.576 · TTFT 7.731 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclaw 1.1.6MLX 4-bit
5Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.132,67 tok/s TG
Prefill 1.930 · TTFT 47.978 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ2_XS
6NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
883,69 tok/s TG
Prefill 26.055 · TTFT 1.240 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclawMLX-4bit
7NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
859,79 tok/s TG
Prefill 25.664 · TTFT 1.257 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMgodclaw
8NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
847,47 tok/s TG
Prefill 20.262 · TTFT 1.586 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMgodclaw
9NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
837,10 tok/s TG
Prefill 20.352 · TTFT 1.585 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclawMLX-4bit
10Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
833,31 tok/s TG
Prefill 17.472 · TTFT 5.292 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclawMLX-q4g64
11NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
725,25 tok/s TG
Prefill 16.303 · TTFT 1.813 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclaw 0.27.1NVFP4 W4A16
12NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
709,02 tok/s TG
Prefill 16.443 · TTFT 1.805 ms
10×NVIDIA GeForce RTX 3090AMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclaw 0.27.1NVFP4 W4A16
13NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
708,32 tok/s TG
Prefill 19.583 · TTFT 709 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclawMLX-4bit
14NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
695,91 tok/s TG
Prefill 15.678 · TTFT 892 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclawMLX-4bit
15NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
692,70 tok/s TG
Prefill 19.510 · TTFT 712 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMgodclaw
16NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
689,92 tok/s TG
Prefill 15.701 · TTFT 893 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMgodclaw
17Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
638,58 tok/s TG
Prefill 306 · TTFT 145.278 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ3_XXS
18Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
623,62 tok/s TG
Prefill 19.024 · TTFT 1.534 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclaw 1.1.6MLX-4bit
19Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
572,23 tok/s TG
Prefill 1.826 · TTFT 21.491 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ2_XS
20Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
477,16 tok/s TG
Prefill 18.162 · TTFT 690 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMgodclaw
21NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkKurzaufgaben TTFT - Thinking OFF - Outputlimit 1/5/10 V1
471,33 tok/s TG
Prefill - · TTFT 31 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclaw 1.1.6MLX 4-bit
22NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
466,72 tok/s TG
Prefill 12.079 · TTFT 1.048 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclaw 0.27.1NVFP4 W4A16
23NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
462,42 tok/s TG
Prefill 11.388 · TTFT 1.082 ms
5×NVIDIA GeForce RTX 3090AMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclaw 0.27.1NVFP4 W4A16
24Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
448,85 tok/s TG
Prefill 14.780 · TTFT 853 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclawMLX-q4g64
25gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
448,17 tok/s TG
Prefill 5.809 · TTFT 3.494 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_M
26Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
447,97 tok/s TG
Prefill 14.674 · TTFT 850 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMgodclaw
27Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
446,60 tok/s TG
Prefill 14.822 · TTFT 850 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclaw 1.1.6MLX-4bit
28Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
385,85 tok/s TG
Prefill 16.933 · TTFT 1.925 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclaw
29Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
371,66 tok/s TG
Prefill 8.745 · TTFT 3.710 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_M
30gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
361,70 tok/s TG
Prefill 4.756 · TTFT 2.076 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_M
31Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
356,01 tok/s TG
Prefill 10.663 · TTFT 3.085 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclaw
32Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
341,53 tok/s TG
Prefill 4.662 · TTFT 4.820 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_M
33Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
319,40 tok/s TG
Prefill 254 · TTFT 73.516 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ3_XXS
34Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
303,07 tok/s TG
Prefill 6.279 · TTFT 2.200 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_M
35Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
299,90 tok/s TG
Prefill 3.515 · TTFT 2.858 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_M
36NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
244,31 tok/s TG
Prefill 6.632 · TTFT 325 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMgodclaw
37NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
239,60 tok/s TG
Prefill 8.173 · TTFT 263 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclawMLX-4bit
38NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
239,27 tok/s TG
Prefill 8.237 · TTFT 261 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMgodclaw
39Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
237,60 tok/s TG
Prefill 6.106 · TTFT 8.357 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawUD-Q4_K_XL
40NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
235,73 tok/s TG
Prefill 6.703 · TTFT 322 ms
1×NVIDIA GeForce RTX 3090AMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclaw 1.1.6MLX 4-bit
41NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
226,44 tok/s TG
Prefill 6.517 · TTFT 330 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclawMLX-4bit
42Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
223,20 tok/s TG
Prefill 12.589 · TTFT 1.123 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclaw
43NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkKurzaufgaben TTFT - Thinking OFF - Outputlimit 1/5/10 V1
218,77 tok/s TG
Prefill - · TTFT 54 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclaw 0.27.1NVFP4 W4A16
44NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
211,38 tok/s TG
Prefill 5.434 · TTFT 411 ms
1×NVIDIA GeForce RTX 3090AMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclaw 0.27.1NVFP4 W4A16
45gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
211,09 tok/s TG
Prefill 4.232 · TTFT 467 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_M
46NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
210,66 tok/s TG
Prefill 6.076 · TTFT 355 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclaw 0.27.1NVFP4 W4A16
47Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
210,39 tok/s TG
Prefill 7.898 · TTFT 1.797 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclaw
48Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
205,63 tok/s TG
Prefill 5.887 · TTFT 2.145 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawUD-Q4_K_XL
49Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
195,16 tok/s TG
Prefill 4.168 · TTFT 11.306 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ2_XS
50Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
189,23 tok/s TG
Prefill 3.806 · TTFT 640 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_M
51Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
184,18 tok/s TG
Prefill 3.927 · TTFT 11.977 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ2_XS
52NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
175,99 tok/s TG
Prefill 6.612 · TTFT 326 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclaw 1.1.6MLX 4-bit
53Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
172,41 tok/s TG
Prefill 2.763 · TTFT 700 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_M
54Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
165,01 tok/s TG
Prefill 3.471 · TTFT 3.864 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ2_XS
55Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
164,49 tok/s TG
Prefill 3.209 · TTFT 4.175 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ2_XS
56Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
154,69 tok/s TG
Prefill 7.524 · TTFT 257 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMgodclaw
57Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
146,54 tok/s TG
Prefill 6.032 · TTFT 320 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMgodclaw
58Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
145,72 tok/s TG
Prefill 6.273 · TTFT 308 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclawMLX-q4g64
59NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
139,97 tok/s TG
Prefill 1.744 · TTFT 14.686 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_M
60Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
132,71 tok/s TG
Prefill 6.165 · TTFT 313 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMtensorfoldgodclaw 1.1.6MLX-4bit
61NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
119,24 tok/s TG
Prefill 1.181 · TTFT 9.551 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_M
62Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
116,39 tok/s TG
Prefill 1.389 · TTFT 1.421 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ2_XS
63Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
108,46 tok/s TG
Prefill 1.445 · TTFT 1.367 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ2_XS
64Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
107,01 tok/s TG
Prefill 3.668 · TTFT 6.469 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclawAWQ
65Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
106,22 tok/s TG
Prefill 3.297 · TTFT 7.376 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclawAWQ
66Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
105,94 tok/s TG
Prefill 3.492 · TTFT 6.829 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclawAWQ
67Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
105,73 tok/s TG
Prefill 2.339 · TTFT 824 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawUD-Q4_K_XL
68Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
104,80 tok/s TG
Prefill 1.364 · TTFT 1.448 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ2_XS
69Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
102,99 tok/s TG
Prefill 3.096 · TTFT 7.876 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclawAWQ
70Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
102,41 tok/s TG
Prefill 3.120 · TTFT 7.835 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclawAWQ
71NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
101,04 tok/s TG
Prefill 1.039 · TTFT 2.074 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_M
72Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
91,92 tok/s TG
Prefill 3.113 · TTFT 7.635 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclaw 0.27.1AWQ
73Llama-3.1-Nemotron-Nano-4B-v1.14.5BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
86,25 tok/s TG
Prefill 8.339 · TTFT 298 ms
1×NVIDIA GeForce RTX 3090AMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclaw
74Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
72,43 tok/s TG
Prefill 2.659 · TTFT 3.956 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclawAWQ
75Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
72,07 tok/s TG
Prefill 2.389 · TTFT 4.453 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclawAWQ
76Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
71,96 tok/s TG
Prefill 2.540 · TTFT 4.155 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclawAWQ
77Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
71,06 tok/s TG
Prefill 2.421 · TTFT 9.812 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclawAWQ
78Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
71,01 tok/s TG
Prefill 2.225 · TTFT 4.791 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclawAWQ
79Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
70,89 tok/s TG
Prefill 2.246 · TTFT 4.750 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMgodclawAWQ
Agent- & Chat-Bewertung

Harnessbenchmark

1 veroeffentlichte Harness-Läufe auf NVIDIA GeForce RTX 3090.

Im Leaderboard →
Messwert:
#Modell / HerstellerMesswerteGPU / CPU / RAMRuntime
1Nemotron-Cascade-2-30B-A3B30BNVIDIA HarnessbenchmarkDecision-Benchmark V 1.0
159 Pkt
79,5% · 159/200 Aufg. · 21,0 s
NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMvLLMvllmAWQ

← Alle Hardware

Technische Daten

Technische Daten – NVIDIA GeForce RTX 3090

HerstellerNVIDIA
ArchitekturAmpere
VRAM24 GB
Tensor-Recheneinheiten328
Speicherbandbreite936 GB/s
TDP350 W
PCIe4.0
Release09/2020
Beste Generation3.484,3 tok/s
Bester Prefill26.055 tok/s
Modelle8
Messläufe (Performance)93