Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
Contributed byMario AlkaQwen (Alibaba)

Qwen3-30B-A3B-Thinking-2507

Performance benchmark · measured on 23.07.2026 22:39

Benchmark-IDrun-20260724-004605-09fb68
Timebench 3 - Kombi (Prefill + Generation)MoE30BRuntime: vLLMQuantisierung: AWQ
Generation625,71tok/s
Prefill31.724,43tok/s
Time to First Token395,50ms
Total duration17,17s
Concurrency5parallel
Ranking in the field
55of 597 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s)

This run is better than 91 % of all comparable systems.
Generation 625,7 tok/s
+156 % vs Ø 244,1
Prefill 31.724,4 tok/s
+493 % vs Ø 5.353,8
Time to First Token 396 ms
-97 % vs Ø 13.148
Distribution in the field0 – 1.444 tok/s
Ø 244 Median Dieser Lauf

Wie schlägt sich dieser Benchmark?

gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260723-194447-dc199d
1.443,9 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004604-1c9023
1.386,8 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260723-045447-edeed3
1.295,3 tok/s
Qwen3-Coder-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004606-ebf474
1.070,6 tok/s
Qwen3-VL-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004607-c49303
1.028,5 tok/s
Ministral-3-14B-Reasoning-2512NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260723-195749-eebab2
1.015,7 tok/s
Qwen3-Coder-30B-A3B-InstructNVIDIA GeForce RTX 5090 · run-20260723-045450-366dae
966,2 tok/s
Qwen3-30B-A3B-Instruct-2507NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004604-860045
961,5 tok/s
Codestral-22B-v0.1NVIDIA GeForce RTX 5090 · run-20260724-004612-002f8b
945,4 tok/s
Devstral-Small-2-24B-Instruct-2512NVIDIA GeForce RTX 5090 · run-20260724-004615-7fac5f
924,8 tok/s
Qwen3-Omni-30B-A3B-ThinkingNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004611-a583d6
910,7 tok/s
Qwen3-30B-A3B-Instruct-2507NVIDIA GeForce RTX 5090 · run-20260723-045450-e8df4d
909,3 tok/s
Qwen3-30B-A3B-Thinking-2507 same modelNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004605-f9a3a1
906,0 tok/s
Qwen3-30B-A3B-Instruct-2507NVIDIA GeForce RTX 3090 Ti · run-20260724-004603-3aec22
901,9 tok/s
Qwen3-30B-A3B-Thinking-2507 this runNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004605-09fb68
625,7 tok/s

Hardware

GPU: NVIDIA RTX PRO 6000 Blackwell Workstation Edition · 96 GB VRAM
CPU: 32x AMD Ryzen 9 9950X 16-Core Processor
RAM: 92 GB

Setup

Runtime: vLLM
Quantization: AWQ
Model: Qwen3-30B-A3B-Thinking-2507

Configuration

benchmark-konfiguration — run-20260724-004605-09fb68
# LLM-Benchmark Konfiguration # Modell : Qwen3-30B-A3B-Thinking-2507 # Engine : vLLM # Run-ID : run-20260724-004605-09fb68 # GPU : NVIDIA RTX PRO 6000 Blackwell Workstation Edition # CPU : 32x AMD Ryzen 9 9950X 16-Core Processor # RAM : 92 GB bench@llm-benchmark:~$ /home/godcore/minimax-vllm-nightly/.venv/bin/python /home/godcore/minimax-vllm-nightly/.venv/bin/vllm serve cyankiwi/Qwen3-30B-A3B-Thinking-2507-AWQ-4bit \ --served-model-name Qwen3-30B-A3B-Thinking-2507 \ --dtype auto \ --max-model-len 8192 \ --gpu-memory-utilization 0.90 \ --trust-remote-code \ --host 0.0.0.0 \ --port 8000
Engine?Die Inferenz-Software, die das Modell ausliefert (z.B. vLLM oder llama.cpp). Sie bestimmt Geschwindigkeit, unterstuetzte Modellformate und welche Parameter ueberhaupt verfuegbar sind.vllm
Modellalias?Der Name, unter dem das Modell ueber die API angesprochen wird. Genau dieser Wert muss im Request-Feld 'model' stehen.Qwen3-30B-A3B-Thinking-2507
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.8192
Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen.Qwen3-30B-A3B-Thinking-2507
Dtype?Zahlenformat der Modellgewichte bei der Berechnung (z.B. auto, float16, bfloat16). 'auto' waehlt automatisch das vom Modell empfohlene Format.auto
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.8192
GPU-Speicher?Anteil des GPU-Speichers (0 bis 1), den vLLM belegen darf. 0.92 = 92 %. Hoeher = mehr Platz fuer den KV-Cache (mehr/laengere parallele Anfragen), aber groesseres Risiko fuer 'Out of Memory'.0.90

All benchmarks of this model To leaderboard

Model comparison

Qwen3-30B-A3B-Thinking-2507 on various hardware

All published performance runs of this model – each bubble a variant: position = prefill (X) × generation (Y), bubble size = number of runs. Closer to the top right = faster. ★ Marked gold = this benchmark.

GPUby graphics card

1.1768825882940,0011.19822.39733.595Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 3090 Ti - 883,7 tok/s Generation, 6.954 tok/s Prefill, TTFT 2.503 ms (15 Laufe)NVIDIA GeForce RTX 30...NVIDIA GeForce RTX 5090 - 873,7 tok/s Generation, 20.565 tok/s Prefill, TTFT 967 ms (3 Laufe)NVIDIA GeForce RTX 50...AMD Radeon AI PRO R9700 - 231,1 tok/s Generation, 4.030 tok/s Prefill, TTFT 1.973 ms (10 Laufe)AMD Radeon AI PRO R97...AMD Radeon 8060S Graphics - 131,2 tok/s Generation, 1.375 tok/s Prefill, TTFT 8.315 ms (3 Laufe)AMD Radeon 8060S Grap...CPU-only - 8,5 tok/s Generation, 74 tok/s Prefill, TTFT 134.321 ms (3 Laufe)CPU-onlyNVIDIA RTX PRO 6000 Blackwell Workstation Edition - 906,0 tok/s Generation, 27.103 tok/s Prefill, TTFT 608 ms (3 Laufe) | DIESER LAUF★ NVIDIA RTX PRO 6000 B...
★ NVIDIA RTX PRO 6000 Blackwell Workstation Edition 906,0 tok/s this runNVIDIA GeForce RTX 3090 Ti 883,7 tok/sNVIDIA GeForce RTX 5090 873,7 tok/sAMD Radeon AI PRO R9700 231,1 tok/sAMD Radeon 8060S Graphics 131,2 tok/sCPU-only 8,5 tok/s

CPUby processor

1.1768825882940,0011.19822.39733.595Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 8945HX with Radeon Graphics - 883,7 tok/s Generation, 6.954 tok/s Prefill, TTFT 2.503 ms (15 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen 7 5800X3D 8-Core Processor - 873,7 tok/s Generation, 20.565 tok/s Prefill, TTFT 967 ms (3 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 231,1 tok/s Generation, 4.030 tok/s Prefill, TTFT 1.973 ms (10 Laufe)AMD Ryzen Threadrippe...AMD RYZEN AI MAX+ 395 w/ Radeon 8060S - 131,2 tok/s Generation, 1.375 tok/s Prefill, TTFT 8.315 ms (3 Laufe)AMD RYZEN AI MAX+ 395...Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 8,5 tok/s Generation, 74 tok/s Prefill, TTFT 134.321 ms (3 Laufe)Intel(R) Xeon(R) CPU ...AMD Ryzen 9 9950X 16-Core Processor - 906,0 tok/s Generation, 27.103 tok/s Prefill, TTFT 608 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 9 9950X 16-...
★ AMD Ryzen 9 9950X 16-Core Processor 906,0 tok/s this runAMD Ryzen 9 8945HX with Radeon Graphics 883,7 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 873,7 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 231,1 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 131,2 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 8,5 tok/s

MBby mainboard

1.1768825882940,004.8639.72714.590Prefill (tok/s)Generation (tok/s)unbekannt - 906,0 tok/s Generation, 11.777 tok/s Prefill, TTFT 2.013 ms (21 Laufe)unbekanntASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 231,1 tok/s Generation, 4.030 tok/s Prefill, TTFT 1.973 ms (10 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd SHWSA (MS-S1 MAX) - 131,2 tok/s Generation, 1.375 tok/s Prefill, TTFT 8.315 ms (3 Laufe)Meigao Innovation Tec...Dell Inc. PowerEdge R820 - 8,5 tok/s Generation, 74 tok/s Prefill, TTFT 134.321 ms (3 Laufe)Dell Inc. PowerEdge R...
unbekannt 906,0 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 231,1 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd SHWSA (MS-S1 MAX) 131,2 tok/sDell Inc. PowerEdge R820 8,5 tok/s

ENGby engine

1.0838876904942981.5256.57111.61716.663Prefill (tok/s)Generation (tok/s)llama.cpp - 474,7 tok/s Generation, 4.148 tok/s Prefill, TTFT 19.973 ms (23 Laufe)llama.cppvLLM - 906,0 tok/s Generation, 14.040 tok/s Prefill, TTFT 2.181 ms (14 Laufe) | DIESER LAUF★ vLLM
★ vLLM 906,0 tok/s this runllama.cpp 474,7 tok/s

DRVby driver

1.1528645762880,008.41816.83525.253Prefill (tok/s)Generation (tok/s)unbekannt - 906,0 tok/s Generation, 8.850 tok/s Prefill, TTFT 21.063 ms (21 Laufe)unbekanntNVIDIA 580.159.03 / CUDA 13.0 - 873,7 tok/s Generation, 20.565 tok/s Prefill, TTFT 967 ms (3 Laufe)NVIDIA 580.159.03 / C...AMD 7.0.0-27-generic - 231,1 tok/s Generation, 4.030 tok/s Prefill, TTFT 1.973 ms (10 Laufe)AMD 7.0.0-27-genericROCm 7.2.0 - 131,2 tok/s Generation, 1.375 tok/s Prefill, TTFT 8.315 ms (3 Laufe)ROCm 7.2.0
unbekannt 906,0 tok/sNVIDIA 580.159.03 / CUDA 13.0 873,7 tok/sAMD 7.0.0-27-generic 231,1 tok/sROCm 7.2.0 131,2 tok/s
Contributed by

Mario Alka Administrator

@marioalka

Gruender von godcore.de und Betreiber von llm-benchmark.de. Ich teste KI-Sprachmodelle auf echter Hardware, messe Tempo (Token/s) und Aufgaben-Qualitaet und teile die Ergebnisse offen und reproduzierbar.