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

NVIDIA GeForce RTX 3090

NVIDIA24 GB VRAM
34Benchmarks
6Models
33Performance
1Harness
350 WMax power
Best generation
3.484,3 tok/s
NVIDIA-Nemotron-3.5-Lightning-30B-A3B
∅ Generation
582,3 tok/s
Schnitt aus 33 Läufen
Best prefill
16.443 tok/s
Prompt processing
Best TTFT
31 ms
Time to First Token
Best harness rate
80%
1 Harness-Läufe
🏆
NVIDIA-Nemotron-3.5-Lightning-30B-A3B läuft am schnellsten auf dieser GPU · 3.484,3 tok/s
Bester Prefill: 16.443 tok/s · 6 Modelle getestet

Top models

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
gpt-oss-20b20B
448,2 tok/s
Qwen3-30B-A3B-Thinking-250730B
371,7 tok/s
Qwen3.6-35B-A3B35B
341,5 tok/s
gpt-oss-120b120B
18,1 tok/s
Anzeige
Performance profile

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

4.5263.3952.2631.1320,003.2106.4209.631Prefill (tok/s)Generation (tok/s)NVIDIA-Nemotron-3.5-Lightning-30B-A3B - 3.484,3 tok/s Generation, 7.781 tok/s Prefill, TTFT 4.659 ms (17 Laufe)NVIDIA-Nemotron-3.5-L...Qwen3.8-Flash-Next - 1.132,7 tok/s Generation, 968 tok/s Prefill, TTFT 51.682 ms (6 Laufe)Qwen3.8-Flash-Nextgpt-oss-20b - 448,2 tok/s Generation, 4.932 tok/s Prefill, TTFT 2.012 ms (3 Laufe)gpt-oss-20bQwen3-30B-A3B-Thinking-2507 - 371,7 tok/s Generation, 6.276 tok/s Prefill, TTFT 2.183 ms (3 Laufe)Qwen3-30B-A3B-Thinkin...Qwen3.6-35B-A3B - 341,5 tok/s Generation, 3.647 tok/s Prefill, TTFT 2.792 ms (3 Laufe)Qwen3.6-35B-A3Bgpt-oss-120b - 18,1 tok/s Generation, 96 tok/s Prefill, TTFT 20.531 ms (1 Lauf)gpt-oss-120b
NVIDIA-Nemotron-3.5-Lightning-30B-A3B 3.484,3 tok/sQwen3.8-Flash-Next 1.132,7 tok/sgpt-oss-20b 448,2 tok/sQwen3-30B-A3B-Thinking-2507 371,7 tok/sQwen3.6-35B-A3B 341,5 tok/sgpt-oss-120b 18,1 tok/s

ENGnach Engine

4.4403.3302.2201.1100,004.6079.21513.822Prefill (tok/s)Generation (tok/s)tensorfold - 3.484,3 tok/s Generation, 7.504 tok/s Prefill, TTFT 6.619 ms (7 Laufe)tensorfoldstrata - 1.132,7 tok/s Generation, 968 tok/s Prefill, TTFT 51.682 ms (6 Laufe)stratavLLM - 725,3 tok/s Generation, 11.287 tok/s Prefill, TTFT 938 ms (7 Laufe)vLLMllama.cpp - 448,2 tok/s Generation, 3.740 tok/s Prefill, TTFT 5.216 ms (13 Laufe)llama.cpp
tensorfold 3.484,3 tok/sstrata 1.132,7 tok/svLLM 725,3 tok/sllama.cpp 448,2 tok/s

CPUnach Prozessor

3.8333.6593.4843.3103.1365.0695.2855.5015.717Prefill (tok/s)Generation (tok/s)AMD Ryzen 5 5600X 6-Core Processor - 3.484,3 tok/s Generation, 5.393 tok/s Prefill, TTFT 13.054 ms (33 Laufe)AMD Ryzen 5 5600X 6-C...
AMD Ryzen 5 5600X 6-Core Processor 3.484,3 tok/s
Throughput & latency

Performancebenchmark

33 veroeffentlichte Performance-Läufe auf NVIDIA GeForce RTX 3090.

In the leaderboard →
Metric:
Size
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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-bitDetails →
2NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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-bitDetails →
3NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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-bitDetails →
4NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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-bitDetails →
5Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 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_XSDetails →
6NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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 W4A16Details →
7NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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 W4A16Details →
8Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 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_XXSDetails →
9Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 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_XSDetails →
10NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkKurzaufgaben 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-bitDetails →
11NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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 W4A16Details →
12NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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 W4A16Details →
13gpt-oss-20b20BOpenAI Performance benchmarkTimebench 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_MDetails →
14Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 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_MDetails →
15gpt-oss-20b20BOpenAI Performance benchmarkTimebench 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_MDetails →
16Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 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_MDetails →
17Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 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_XXSDetails →
18Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 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_MDetails →
19Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 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_MDetails →
20NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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-bitDetails →
21NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkKurzaufgaben 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 W4A16Details →
22NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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 W4A16Details →
23gpt-oss-20b20BOpenAI Performance benchmarkTimebench 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_MDetails →
24NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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 W4A16Details →
25Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 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_MDetails →
26NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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-bitDetails →
27Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 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_MDetails →
28NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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_MDetails →
29NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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_MDetails →
30Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 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_XSDetails →
31NVIDIA-Nemotron-3.5-Lightning-30B-A3B31.6BNVIDIA Performance benchmarkTimebench 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_MDetails →
32Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
50,53 tok/s TG
Prefill 106 · TTFT 20.413 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ3_XXSDetails →
33gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
18,07 tok/s TG
Prefill 96 · TTFT 20.531 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_MDetails →
Agent & chat rating

Harnessbenchmark

1 veroeffentlichte Harness-Läufe auf NVIDIA GeForce RTX 3090.

In the leaderboard →
Metric:
#Model / MakerMetricsGPU / CPU / RAMRuntime
1Nemotron-Cascade-2-30B-A3B30BNVIDIA Harness benchmarkDecision-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 RAMvLLMvllmAWQDetails →

← All hardware

Technische Daten

Technische Daten – NVIDIA GeForce RTX 3090

HerstellerNVIDIA
ArchitekturAmpere
VRAM24 GB
Tensor-Recheneinheiten328
Speicherbandbreite936 GB/s
TDP350 W
PCIe4.0
Release09/2020
Best generation3.484,3 tok/s
Best prefill16.443 tok/s
Models6
Messläufe (Performance)33