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

Qwen3-Omni-30B-A3B-Thinking

Performance benchmark · measured on 23.07.2026 23:46

Benchmark-IDrun-20260724-004611-a583d6
Timebench 3 - Kombi (Prefill + Generation)MoE30BRuntime: vLLMQuantisierung: AWQ
Generation910,74tok/s
Prefill33.906,66tok/s
Time to First Token1.527,00ms
Total duration25,70s
Concurrency10parallel
Ranking in the field
39of 80 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 10× concurrent

This run is better than 52 % of all comparable systems.
Generation 910,7 tok/s
0 % vs Ø 911,1
Prefill 33.906,7 tok/s
+266 % vs Ø 9.268,3
Time to First Token 1.527 ms
-96 % vs Ø 34.047
Distribution in the field0 – 2.414 tok/s
Ø 911 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-b37ed9
2.414,4 tok/s
Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-4cca42
2.182,7 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-9c966e
1.995,4 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-8007c4
1.993,5 tok/s
Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032119-311459
1.791,5 tok/s
Nemotron-3-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032121-e2403f
1.773,5 tok/s
Nemotron-Cascade-2-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032120-1b1a49
1.768,1 tok/s
gemma-4-E4B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-866815
1.758,6 tok/s
Laguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-9f055e
1.757,4 tok/s
Laguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-f34b37
1.753,8 tok/s
Laguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-1e8c74
1.740,4 tok/s
Qwen3-Coder-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032124-ef2bb1
1.690,0 tok/s
Qwen3-30B-A3B-Thinking-2507NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032123-88fa84
1.670,5 tok/s
Qwen3-30B-A3B-Instruct-2507NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032122-3d6d17
1.658,1 tok/s
Qwen3-Omni-30B-A3B-Thinking this runNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004611-a583d6
910,7 tok/s

How does this benchmark compare on other GPUs?

Same model on different hardware · 10× concurrent · Generation (tok/s)

Configuration

benchmark-konfiguration — run-20260724-004611-a583d6
# LLM-Benchmark Konfiguration # Modell : Qwen3-Omni-30B-A3B-Thinking # Engine : vLLM # Run-ID : run-20260724-004611-a583d6 # GPU : NVIDIA RTX PRO 6000 Blackwell Workstation Edition # CPU : 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-Omni-30B-A3B-Thinking-AWQ-4bit \ --served-model-name Qwen3-Omni-30B-A3B-Thinking \ --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-Omni-30B-A3B-Thinking
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-Omni-30B-A3B-Thinking
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

Anzeige
Model comparison

Qwen3-Omni-30B-A3B-Thinking 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

2.1441.6081.0725360,006.82413.64720.471Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 5090 - 1.673,6 tok/s Generation, 8.080 tok/s Prefill, TTFT 3.494 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 1.512,4 tok/s Generation, 9.978 tok/s Prefill, TTFT 3.553 ms (9 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 Ti - 927,4 tok/s Generation, 4.493 tok/s Prefill, TTFT 6.216 ms (3 Laufe)NVIDIA GeForce RTX 30...NVIDIA RTX A6000 - 560,9 tok/s Generation, 12.527 tok/s Prefill, TTFT 1.951 ms (27 Laufe)NVIDIA RTX A6000AMD Radeon PRO W7800 48GB - 205,1 tok/s Generation, 3.827 tok/s Prefill, TTFT 2.611 ms (4 Laufe)AMD Radeon PRO W7800 ...AMD Radeon AI PRO R9700 - 160,6 tok/s Generation, 2.844 tok/s Prefill, TTFT 74.394 ms (13 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 5070 Ti - 155,9 tok/s Generation, 947 tok/s Prefill, TTFT 35.680 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.653,3 tok/s Generation, 16.646 tok/s Prefill, TTFT 2.042 ms (6 Laufe) | DIESER LAUF★ NVIDIA RTX PRO 6000 B...
NVIDIA GeForce RTX 5090 1.673,6 tok/s★ NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.653,3 tok/s this runNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.512,4 tok/sNVIDIA GeForce RTX 3090 Ti 927,4 tok/sNVIDIA RTX A6000 560,9 tok/sAMD Radeon PRO W7800 48GB 205,1 tok/sAMD Radeon AI PRO R9700 160,6 tok/sNVIDIA GeForce RTX 5070 Ti 155,9 tok/s

CPUby processor

2.1351.6011.0675340,006.72513.45020.175Prefill (tok/s)Generation (tok/s)AMD Ryzen 7 5800X3D 8-Core Processor - 1.673,6 tok/s Generation, 8.080 tok/s Prefill, TTFT 3.494 ms (3 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 1.512,4 tok/s Generation, 9.978 tok/s Prefill, TTFT 3.553 ms (9 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 927,4 tok/s Generation, 4.493 tok/s Prefill, TTFT 6.216 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 560,9 tok/s Generation, 9.380 tok/s Prefill, TTFT 25.495 ms (40 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 205,1 tok/s Generation, 2.593 tok/s Prefill, TTFT 16.783 ms (7 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 9950X 16-Core Processor - 1.653,3 tok/s Generation, 16.646 tok/s Prefill, TTFT 2.042 ms (6 Laufe) | DIESER LAUF★ AMD Ryzen 9 9950X 16-...
AMD Ryzen 7 5800X3D 8-Core Processor 1.673,6 tok/s★ AMD Ryzen 9 9950X 16-Core Processor 1.653,3 tok/s this runAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.512,4 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 927,4 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 560,9 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 205,1 tok/s

MBby mainboard

2.1351.6011.0675340,006.72513.45020.175Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 1.673,6 tok/s Generation, 8.080 tok/s Prefill, TTFT 3.494 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 1.512,4 tok/s Generation, 9.490 tok/s Prefill, TTFT 21.465 ms (49 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 927,4 tok/s Generation, 4.493 tok/s Prefill, TTFT 6.216 ms (3 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 205,1 tok/s Generation, 2.593 tok/s Prefill, TTFT 16.783 ms (7 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 1.653,3 tok/s Generation, 16.646 tok/s Prefill, TTFT 2.042 ms (6 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.673,6 tok/s★ ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.653,3 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.512,4 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 927,4 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 205,1 tok/s

ENGby engine

2.1691.6271.0845420,02.2258.55314.88221.210Prefill (tok/s)Generation (tok/s)llama.cpp - 1.673,6 tok/s Generation, 6.666 tok/s Prefill, TTFT 22.980 ms (52 Laufe)llama.cppunbekannt - 34,8 tok/s Generation, 5.528 tok/s Prefill, TTFT 767 ms (1 Lauf)unbekanntvLLM - 910,7 tok/s Generation, 17.908 tok/s Prefill, TTFT 994 ms (15 Laufe) | DIESER LAUF★ vLLM
llama.cpp 1.673,6 tok/s★ vLLM 910,7 tok/s this rununbekannt 34,8 tok/s

DRVby driver

2.1691.6271.0845420,04.3196.3438.36710.391Prefill (tok/s)Generation (tok/s)unbekannt - 1.673,6 tok/s Generation, 9.182 tok/s Prefill, TTFT 18.058 ms (67 Laufe)unbekanntAMD 7.0.0-27-generic - 34,8 tok/s Generation, 5.528 tok/s Prefill, TTFT 767 ms (1 Lauf)AMD 7.0.0-27-generic
unbekannt 1.673,6 tok/sAMD 7.0.0-27-generic 34,8 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (10× concurrent). Methodology →

⚙️ ConfigurationAll metrics and charts below follow these settings – based on a 24-month runtime.Save to URLReset
⚡ Electricity price EUR/kWh
⚙️ System utilization 100 %
🖥️ Acquisition EUR
🔌 Idle 70 W
⚡ TDP 644 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)644 W estimated (TDP)GPU 600 + CPU 29 + Board 15 W full load
Avg cost / hourEUR 0.19
Electricity / 1M tokensEUR 0.059
Token / kWh5.09M
Acquisition (system)EUR 15,248 full priceGPU EUR 13,000 · CPU EUR 649 · Board EUR 499 · RAM EUR 920 · PSU EUR 180
Electricity (2 years)
TCO (2 years)EUR 18,632
Output tokens (2 years)57.44B
☁️ External LLM (API) – comparison
External LLM cost (2 years)
Savings vs. external (2 years)

All values above and the charts below take the configured system utilization into account: at X% the system generates only X% of the time, the rest it idles (70 W). Cost per hour drops (more idle), cost per token rises.

Cost over 2 years – electricity only

Cost over 2 years – incl. acquisition (TCO)

Speed vs. tokens per euro

Euro per 1M tokens

Comparison vs. API – economics per benchmark

Qwen3-Omni-30B-A3B-ThinkingNVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen3-Omni-30B-A3B-ThinkingNVIDIA GeForce RTX 5090Qwen3-Omni-30B-A3B-ThinkingNVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen3-Omni-30B-A3B-Thinking3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
Electricity cost (24 mo.)
Acquisition cost
Total cost (TCO)
Generated tokens (24 mo.)
Token price via API
Break-even point (days)
Result (savings / extra cost)

Comparison with up to 3 next-best runs of this model at the same concurrency (at least one on different hardware). Power = GPU TDP + CPU (idle + 15 %) + board (estimated), acquisition = full system (GPU + CPU + board + RAM + PSU), prices = stored market prices.

Contributed by

Mario Alka Administrator

@marioalka

Ich bin Unternehmer, Softwareentwickler und KI-Enthusiast. Seit vielen Jahren entwickle ich Unternehmenssoftware und beschäftige mich inzwischen fast täglich mit lokalen LLMs, KI-Agenten und leistungsfähiger KI-Hardware.

Mit LLM-Benchmark.de möchte ich eine Plattform schaffen, auf der Modelle, GPUs und Agenten objektiv und reproduzierbar miteinander verglichen werden.