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

NVIDIA GeForce RTX 5090

NVIDIA32 GB VRAM
★★★★★5,0/ 5 · Bewertung
218Benchmarks
50Models
218Performance
0Harness
30 WIdle power
575 WMax power
Best generation
2.491,2 tok/s
gemma-4-E2B-it
∅ Generation
429,9 tok/s
Schnitt aus 218 Läufen
Best prefill
37.116 tok/s
Prompt processing
Best TTFT
119 ms
Time to First Token
Best harness rate
–%
noch kein Harness
🏆
gemma-4-E2B-it läuft am schnellsten auf dieser GPU · 2.491,2 tok/s
Bester Prefill: 37.116 tok/s · 50 Modelle getestet

Top models

Bester gemessener Durchsatz je Modell auf NVIDIA GeForce RTX 5090 – umschaltbar nach Generation, Prefill oder Kombiwert.

gemma-4-E2B-it5B
2.491,2 tok/s
gpt-oss-20b20B
1.890,7 tok/s
Nemotron-3-Nano-4B4B
1.878,7 tok/s
Laguna-XS-2.1
1.765,0 tok/s
Nemotron-3-Nano-30B-A3B30B
1.722,1 tok/s
Nemotron-Cascade-2-30B-A3B30B
1.719,2 tok/s
Qwen3-Coder-30B-A3B-Instruct30B
1.716,6 tok/s
Nemotron-3-Nano-Omni-30B-A3B-Reasoning30B
1.706,7 tok/s
Qwen3-30B-A3B-Thinking-250730B
1.683,8 tok/s
Qwen3-Omni-30B-A3B-Thinking30B
1.673,6 tok/s
Anzeige
Performance profile

Durchsatz auf NVIDIA GeForce RTX 5090

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

MODnach Modell

3.1442.3581.5727860,008.12416.24824.372Prefill (tok/s)Generation (tok/s)gemma-4-E2B-it - 2.491,2 tok/s Generation, 11.148 tok/s Prefill, TTFT 2.175 ms (3 Laufe)gemma-4-E2B-itgpt-oss-20b - 1.890,7 tok/s Generation, 13.890 tok/s Prefill, TTFT 1.326 ms (13 Laufe)gpt-oss-20bNemotron-3-Nano-4B - 1.878,7 tok/s Generation, 5.348 tok/s Prefill, TTFT 3.511 ms (3 Laufe)Nemotron-3-Nano-4BLaguna-XS-2.1 - 1.765,0 tok/s Generation, 8.116 tok/s Prefill, TTFT 5.317 ms (6 Laufe)Laguna-XS-2.1Nemotron-3-Nano-30B-A3B - 1.722,1 tok/s Generation, 5.965 tok/s Prefill, TTFT 3.591 ms (3 Laufe)Nemotron-3-Nano-30B-A...Nemotron-Cascade-2-30B-A3B - 1.719,2 tok/s Generation, 6.140 tok/s Prefill, TTFT 3.569 ms (3 Laufe)Nemotron-Cascade-2-30...Qwen3-Coder-30B-A3B-Instruct - 1.716,6 tok/s Generation, 19.347 tok/s Prefill, TTFT 3.628 ms (3 Laufe)Qwen3-Coder-30B-A3B-I...Nemotron-3-Nano-Omni-30B-A3B-Reasoning - 1.706,7 tok/s Generation, 5.892 tok/s Prefill, TTFT 3.614 ms (3 Laufe)Nemotron-3-Nano-Omni-...Qwen3-30B-A3B-Thinking-2507 - 1.683,8 tok/s Generation, 17.898 tok/s Prefill, TTFT 3.147 ms (4 Laufe)Qwen3-30B-A3B-Thinkin...Qwen3-Omni-30B-A3B-Thinking - 1.673,6 tok/s Generation, 8.945 tok/s Prefill, TTFT 5.049 ms (2 Laufe)Qwen3-Omni-30B-A3B-Th...Qwen3-30B-A3B-Instruct-2507 - 1.671,0 tok/s Generation, 19.676 tok/s Prefill, TTFT 3.011 ms (4 Laufe)Qwen3-30B-A3B-Instruc...Qwen3-VL-30B-A3B-Instruct - 1.655,9 tok/s Generation, 10.958 tok/s Prefill, TTFT 4.792 ms (2 Laufe)Qwen3-VL-30B-A3B-Inst...gemma-4-E4B-it - 1.606,1 tok/s Generation, 11.331 tok/s Prefill, TTFT 4.195 ms (2 Laufe)gemma-4-E4B-itMeta-Llama-3.1-8B-Instruct - 1.593,1 tok/s Generation, 14.449 tok/s Prefill, TTFT 4.670 ms (2 Laufe)Meta-Llama-3.1-8B-Ins...North-Mini-Code-1.0 - 1.557,3 tok/s Generation, 6.685 tok/s Prefill, TTFT 5.701 ms (2 Laufe)North-Mini-Code-1.0Ornith-1.0-35B - 1.556,7 tok/s Generation, 5.850 tok/s Prefill, TTFT 5.607 ms (2 Laufe)Ornith-1.0-35BGemma-4-26B-A4B-it - 1.540,5 tok/s Generation, 4.274 tok/s Prefill, TTFT 6.838 ms (2 Laufe)Gemma-4-26B-A4B-itOrnith-1.0-9B - 1.505,6 tok/s Generation, 7.874 tok/s Prefill, TTFT 5.017 ms (2 Laufe)Ornith-1.0-9BQwen-AgentWorld-35B-A3B - 1.439,1 tok/s Generation, 6.377 tok/s Prefill, TTFT 5.727 ms (2 Laufe)Qwen-AgentWorld-35B-A...Qwen3.5-35B-A3B - 1.416,7 tok/s Generation, 6.188 tok/s Prefill, TTFT 5.634 ms (2 Laufe)Qwen3.5-35B-A3BQwen3.6-35B-A3B - 1.409,4 tok/s Generation, 5.832 tok/s Prefill, TTFT 5.852 ms (2 Laufe)Qwen3.6-35B-A3Bgemma-4-12B-it - 1.058,9 tok/s Generation, 3.300 tok/s Prefill, TTFT 9.224 ms (2 Laufe)gemma-4-12B-itMinistral-3-14B-Reasoning-2512 - 1.028,1 tok/s Generation, 8.785 tok/s Prefill, TTFT 6.897 ms (2 Laufe)Ministral-3-14B-Reaso...Seed-OSS-36B-Instruct - 839,7 tok/s Generation, 3.293 tok/s Prefill, TTFT 27.453 ms (1 Lauf)Seed-OSS-36B-InstructMagistral-Small-2509 - 737,0 tok/s Generation, 152 tok/s Prefill, TTFT 9.120 ms (1 Lauf)Magistral-Small-2509Codestral-22B-v0.1 - 641,4 tok/s Generation, 6.716 tok/s Prefill, TTFT 15.676 ms (1 Lauf)Codestral-22B-v0.1Devstral-Small-2507 - 625,1 tok/s Generation, 9.619 tok/s Prefill, TTFT 11.866 ms (1 Lauf)Devstral-Small-2507Devstral-Small-2-24B-Instruct-2512 - 620,3 tok/s Generation, 8.842 tok/s Prefill, TTFT 15.213 ms (1 Lauf)Devstral-Small-2-24B-...Qwen3.6-27B - 532,5 tok/s Generation, 3.040 tok/s Prefill, TTFT 21.374 ms (1 Lauf)Qwen3.6-27BOpenReasoning-Nemotron-32B - 481,0 tok/s Generation, 4.476 tok/s Prefill, TTFT 22.733 ms (1 Lauf)OpenReasoning-Nemotro...Qwen2.5-Coder-32B-Instruct - 479,6 tok/s Generation, 4.926 tok/s Prefill, TTFT 22.591 ms (1 Lauf)Qwen2.5-Coder-32B-Ins...Qwen2.5-32B-Instruct-AWQ - 473,9 tok/s Generation, 5.066 tok/s Prefill, TTFT 22.401 ms (1 Lauf)Qwen2.5-32B-Instruct-...
gemma-4-E2B-it 2.491,2 tok/sgpt-oss-20b 1.890,7 tok/sNemotron-3-Nano-4B 1.878,7 tok/sLaguna-XS-2.1 1.765,0 tok/sNemotron-3-Nano-30B-A3B 1.722,1 tok/sNemotron-Cascade-2-30B-A3B 1.719,2 tok/sQwen3-Coder-30B-A3B-Instruct 1.716,6 tok/sNemotron-3-Nano-Omni-30B-A3B-Reasoning 1.706,7 tok/sQwen3-30B-A3B-Thinking-2507 1.683,8 tok/sQwen3-Omni-30B-A3B-Thinking 1.673,6 tok/sQwen3-30B-A3B-Instruct-2507 1.671,0 tok/sQwen3-VL-30B-A3B-Instruct 1.655,9 tok/sgemma-4-E4B-it 1.606,1 tok/sMeta-Llama-3.1-8B-Instruct 1.593,1 tok/sNorth-Mini-Code-1.0 1.557,3 tok/sOrnith-1.0-35B 1.556,7 tok/sGemma-4-26B-A4B-it 1.540,5 tok/sOrnith-1.0-9B 1.505,6 tok/sQwen-AgentWorld-35B-A3B 1.439,1 tok/sQwen3.5-35B-A3B 1.416,7 tok/sQwen3.6-35B-A3B 1.409,4 tok/sgemma-4-12B-it 1.058,9 tok/sMinistral-3-14B-Reasoning-2512 1.028,1 tok/sSeed-OSS-36B-Instruct 839,7 tok/sMagistral-Small-2509 737,0 tok/sCodestral-22B-v0.1 641,4 tok/sDevstral-Small-2507 625,1 tok/sDevstral-Small-2-24B-Instruct-2512 620,3 tok/sQwen3.6-27B 532,5 tok/sOpenReasoning-Nemotron-32B 481,0 tok/sQwen2.5-Coder-32B-Instruct 479,6 tok/sQwen2.5-32B-Instruct-AWQ 473,9 tok/s

ENGnach Engine

2.9612.4501.9391.4289173.52012.04420.56829.092Prefill (tok/s)Generation (tok/s)llama.cpp - 2.491,2 tok/s Generation, 7.990 tok/s Prefill, TTFT 6.233 ms (71 Laufe)llama.cppvLLM - 1.386,8 tok/s Generation, 24.621 tok/s Prefill, TTFT 1.144 ms (9 Laufe)vLLM
llama.cpp 2.491,2 tok/svLLM 1.386,8 tok/s

CPUnach Prozessor

2.7402.6162.4912.3672.2429.2709.66410.05910.453Prefill (tok/s)Generation (tok/s)AMD Ryzen 7 5800X3D 8-Core Processor - 2.491,2 tok/s Generation, 9.861 tok/s Prefill, TTFT 5.661 ms (80 Laufe)AMD Ryzen 7 5800X3D 8...
AMD Ryzen 7 5800X3D 8-Core Processor 2.491,2 tok/s
Throughput & latency

Performancebenchmark

80 veroeffentlichte Performance-Läufe auf NVIDIA GeForce RTX 5090.

In the leaderboard →
Metric:
Size
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
2.491,20 tok/s TG
Prefill 15.814 · TTFT 4.382 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
2gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.890,69 tok/s TG
Prefill 14.771 · TTFT 5.489 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
3Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.878,73 tok/s TG
Prefill 7.717 · TTFT 6.690 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
4Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.764,99 tok/s TG
Prefill 8.542 · TTFT 7.776 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
5Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.740,12 tok/s TG
Prefill 8.571 · TTFT 7.786 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
6Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.738,38 tok/s TG
Prefill 8.872 · TTFT 7.722 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
7Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.722,05 tok/s TG
Prefill 7.387 · TTFT 7.500 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
8Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.719,17 tok/s TG
Prefill 8.044 · TTFT 7.376 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
9Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.716,59 tok/s TG
Prefill 12.604 · TTFT 6.861 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
10Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.706,69 tok/s TG
Prefill 7.511 · TTFT 7.506 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
11Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.683,83 tok/s TG
Prefill 10.169 · TTFT 7.361 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
12Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.673,59 tok/s TG
Prefill 9.186 · TTFT 7.567 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
13Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.671,02 tok/s TG
Prefill 11.920 · TTFT 7.068 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
14Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.655,92 tok/s TG
Prefill 10.520 · TTFT 7.269 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
15gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.606,09 tok/s TG
Prefill 12.150 · TTFT 6.323 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
16Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.593,10 tok/s TG
Prefill 16.376 · TTFT 6.849 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
17North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.557,27 tok/s TG
Prefill 6.839 · TTFT 8.511 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_MDetails →
18Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.556,71 tok/s TG
Prefill 6.275 · TTFT 8.228 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
19Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.540,46 tok/s TG
Prefill 4.499 · TTFT 10.048 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_XLDetails →
20Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.505,61 tok/s TG
Prefill 8.190 · TTFT 7.531 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
21Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.439,13 tok/s TG
Prefill 6.706 · TTFT 8.521 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_MDetails →
22Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.416,65 tok/s TG
Prefill 6.608 · TTFT 8.323 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
23Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.409,41 tok/s TG
Prefill 6.434 · TTFT 8.582 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_MDetails →
24gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.386,79 tok/s TG
Prefill 19.981 · TTFT 1.205 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliDetails →
25gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.301,91 tok/s TG
Prefill 13.076 · TTFT 1.540 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
26gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.295,30 tok/s TG
Prefill 25.462 · TTFT 808 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQDetails →
27Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.164,80 tok/s TG
Prefill 6.428 · TTFT 2.540 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
28gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.113,52 tok/s TG
Prefill 13.157 · TTFT 1.764 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
29gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.058,85 tok/s TG
Prefill 3.506 · TTFT 13.704 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_XLDetails →
30Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.028,12 tok/s TG
Prefill 9.053 · TTFT 10.580 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
31Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
992,08 tok/s TG
Prefill 6.249 · TTFT 2.785 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
32Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
990,65 tok/s TG
Prefill 6.523 · TTFT 2.724 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
33Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
986,08 tok/s TG
Prefill 6.401 · TTFT 2.783 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
34Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
972,04 tok/s TG
Prefill 7.593 · TTFT 2.866 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
35Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
966,21 tok/s TG
Prefill 33.768 · TTFT 1.793 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQDetails →
36Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
965,66 tok/s TG
Prefill 7.691 · TTFT 2.852 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
37Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
959,86 tok/s TG
Prefill 7.429 · TTFT 2.902 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
38Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
946,70 tok/s TG
Prefill 11.668 · TTFT 2.231 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
39Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
935,41 tok/s TG
Prefill 8.108 · TTFT 2.626 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
40Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
931,70 tok/s TG
Prefill 11.679 · TTFT 2.264 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
41Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
930,30 tok/s TG
Prefill 8.704 · TTFT 2.532 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
42Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
920,12 tok/s TG
Prefill 11.397 · TTFT 2.315 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
43Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
909,25 tok/s TG
Prefill 37.116 · TTFT 1.783 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQDetails →
44gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
892,60 tok/s TG
Prefill 10.513 · TTFT 2.066 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
45Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
873,72 tok/s TG
Prefill 33.023 · TTFT 1.835 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQDetails →
46Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
867,90 tok/s TG
Prefill 5.424 · TTFT 2.985 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
47gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
848,28 tok/s TG
Prefill 12.860 · TTFT 769 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
48Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
839,78 tok/s TG
Prefill 4.050 · TTFT 3.627 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_XLDetails →
49Seed-OSS-36B-Instruct36BByteDance Seed Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
839,72 tok/s TG
Prefill 3.293 · TTFT 27.453 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
50Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
823,64 tok/s TG
Prefill 12.521 · TTFT 2.492 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
51North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
820,76 tok/s TG
Prefill 6.532 · TTFT 2.890 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_MDetails →
52Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
805,86 tok/s TG
Prefill 7.558 · TTFT 2.503 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
53gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
803,96 tok/s TG
Prefill 16.236 · TTFT 616 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliDetails →
54Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
794,66 tok/s TG
Prefill 5.768 · TTFT 2.945 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
55gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
787,90 tok/s TG
Prefill 14.843 · TTFT 1.365 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
56Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
786,38 tok/s TG
Prefill 6.048 · TTFT 2.933 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_MDetails →
57gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
784,45 tok/s TG
Prefill 17.724 · TTFT 560 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQDetails →
58gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
763,58 tok/s TG
Prefill 14.721 · TTFT 1.432 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
59Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
744,59 tok/s TG
Prefill 5.231 · TTFT 3.123 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_MDetails →
60Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
736,95 tok/s TG
Prefill 152 · TTFT 9.120 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
61gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
669,44 tok/s TG
Prefill 11.783 · TTFT 840 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
62Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
655,83 tok/s TG
Prefill 17.990 · TTFT 931 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQDetails →
63Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
641,39 tok/s TG
Prefill 6.716 · TTFT 15.676 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
64Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
633,41 tok/s TG
Prefill 20.292 · TTFT 767 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQDetails →
65Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
625,05 tok/s TG
Prefill 9.619 · TTFT 11.866 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
66Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
620,27 tok/s TG
Prefill 8.842 · TTFT 15.213 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
67gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
581,69 tok/s TG
Prefill 3.094 · TTFT 4.745 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_XLDetails →
68Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
545,30 tok/s TG
Prefill 8.517 · TTFT 3.214 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
69Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
532,52 tok/s TG
Prefill 3.040 · TTFT 21.374 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
70OpenReasoning-Nemotron-32B32BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
481,00 tok/s TG
Prefill 4.476 · TTFT 22.733 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
71Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
479,62 tok/s TG
Prefill 4.926 · TTFT 22.591 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
72Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
473,90 tok/s TG
Prefill 5.066 · TTFT 22.401 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
73gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
404,59 tok/s TG
Prefill 8.241 · TTFT 257 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
74Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
393,52 tok/s TG
Prefill 1.898 · TTFT 1.302 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
75gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
388,85 tok/s TG
Prefill 2.378 · TTFT 1.888 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
76gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
388,20 tok/s TG
Prefill 8.415 · TTFT 240 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
77gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
377,61 tok/s TG
Prefill 4.553 · TTFT 602 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
78Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
359,35 tok/s TG
Prefill 3.984 · TTFT 549 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
79Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
359,29 tok/s TG
Prefill 3.914 · TTFT 550 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
80Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
359,03 tok/s TG
Prefill 3.976 · TTFT 549 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_MDetails →
Agent & chat rating

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf NVIDIA GeForce RTX 5090.

In the leaderboard →
Noch keine Harnessbenchmarks auf dieser Hardware.

← All hardware

Technische Daten

Technische Daten – NVIDIA GeForce RTX 5090

HerstellerNVIDIA
ArchitekturBlackwell
VRAM32 GB
Tensor-Recheneinheiten680
Speicherbandbreite1.792 GB/s
TDP575 W
PCIe5.0
Release01/2025
Bewertung★★★★★5,0
Best generation2.491,2 tok/s
Best prefill37.116 tok/s
Models50
Messläufe (Performance)218