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

Qwen3-Omni-30B-A3B-Thinking

Performance benchmark · measured on 03.08.2026 20:43

Benchmark-IDrun-20260805-053405-cdbe6c
Timebench 3 - Kombi (Prefill + Generation)MoE30BRuntime: llama.cppQuantisierung: Q4_K_M
Generation67,66tok/s
Prefill232,43tok/s
Time to First Token219.771,50ms
Total duration1.127,47s
Concurrency10parallel
Ranking in the field
70of 123 systems

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

This run is better than 43 % of all comparable systems.
Generation 67,7 tok/s
-55 % vs Ø 149,3
Prefill 232,4 tok/s
-92 % vs Ø 2.767,7
Time to First Token 219.772 ms
+87 % vs Ø 117.654
Distribution in the field2 – 667 tok/s
Ø 148 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

How does this benchmark compare on other GPUs?

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

Hardware

GPU: AMD Radeon AI PRO R9700 · 32 GB VRAM
CPU: AMD Ryzen Threadripper PRO 7955WX 16-Cores
RAM: 184 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Qwen3-Omni-30B-A3B-Thinking

Configuration

benchmark-konfiguration — run-20260805-053405-cdbe6c
# LLM-Benchmark Konfiguration # Modell : Qwen3-Omni-30B-A3B-Thinking # Engine : llama.cpp # Run-ID : run-20260805-053405-cdbe6c # GPU : AMD Radeon AI PRO R9700 # CPU : AMD Ryzen Threadripper PRO 7955WX 16-Cores # RAM : 184 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--ggml-org--Qwen3-Omni-30B-A3B-Thinking-GGUF/snapshots/6807f126832efa5bce2969fec85a80594e21df9d/Qwen3-Omni-30B-A3B-Thinking-Q4_K_M.gguf \ --alias Qwen3-Omni-30B-A3B-Thinking \ --host 0.0.0.0 \ --port 8000 \ -ngl 999 \ -c 16384 \ -np 4 \ --jinja
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.llamacpp
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.16384
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird./home/godcore/.cache/huggingface/hub/models--ggml-org--Qwen3-Omni-30B-A3B-Thinking-GGUF/snapshots/6807f126832efa5bce2969fec85a80594e21df9d/Qwen3-Omni-30B-A3B-Thinking-Q4_K_M.gguf
GPU-Layer?Anzahl der auf die GPU ausgelagerten Modell-Layer. Hoeher = mehr VRAM und schneller; der Rest laeuft auf der CPU. 999 = alles auf GPU.999
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.16384
np4

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 Workstation Edition - 1.653,3 tok/s Generation, 16.646 tok/s Prefill, TTFT 2.042 ms (6 Laufe)NVIDIA RTX PRO 6000 B...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 GeForce RTX 5070 Ti - 155,9 tok/s Generation, 947 tok/s Prefill, TTFT 35.680 ms (3 Laufe)NVIDIA GeForce RTX 50...AMD Radeon AI PRO R9700 - 160,6 tok/s Generation, 2.357 tok/s Prefill, TTFT 87.781 ms (11 Laufe) | DIESER LAUF★ AMD Radeon AI PRO R97...
NVIDIA GeForce RTX 5090 1.673,6 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.653,3 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.512,4 tok/sNVIDIA GeForce RTX 3090 Ti 927,4 tok/s★ AMD Radeon AI PRO R9700 160,6 tok/s this runNVIDIA GeForce RTX 5070 Ti 155,9 tok/s

CPUby processor

2.1441.6081.0725360,006.82413.64720.471Prefill (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 9 9950X 16-Core Processor - 1.653,3 tok/s Generation, 16.646 tok/s Prefill, TTFT 2.042 ms (6 Laufe)AMD Ryzen 9 9950X 16-...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 5975WX 32-Cores - 155,9 tok/s Generation, 947 tok/s Prefill, TTFT 35.680 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 160,6 tok/s Generation, 2.357 tok/s Prefill, TTFT 87.781 ms (11 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 7 5800X3D 8-Core Processor 1.673,6 tok/sAMD Ryzen 9 9950X 16-Core Processor 1.653,3 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.512,4 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 927,4 tok/s★ AMD Ryzen Threadripper PRO 7955WX 16-Cores 160,6 tok/s this runAMD Ryzen Threadripper PRO 5975WX 32-Cores 155,9 tok/s

MBby mainboard

2.1441.6081.0725360,006.82413.64720.471Prefill (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. ProArt X870E-CREATOR WIFI - 1.653,3 tok/s Generation, 16.646 tok/s Prefill, TTFT 2.042 ms (6 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 - 155,9 tok/s Generation, 947 tok/s Prefill, TTFT 35.680 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 1.512,4 tok/s Generation, 5.786 tok/s Prefill, TTFT 49.878 ms (20 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.673,6 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.653,3 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.512,4 tok/s this runMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 927,4 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 155,9 tok/s

ENGby engine

1.9941.6431.2929415911.7038.74015.77722.813Prefill (tok/s)Generation (tok/s)vLLM - 910,7 tok/s Generation, 19.173 tok/s Prefill, TTFT 1.388 ms (5 Laufe)vLLMllama.cpp - 1.673,6 tok/s Generation, 5.343 tok/s Prefill, TTFT 37.968 ms (30 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 1.673,6 tok/s this runvLLM 910,7 tok/s

DRVby driver

1.8411.7571.6741.5901.5066.8807.1737.4657.758Prefill (tok/s)Generation (tok/s)unbekannt - 1.673,6 tok/s Generation, 7.319 tok/s Prefill, TTFT 32.742 ms (35 Laufe)unbekannt
unbekannt 1.673,6 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 85 W
⚡ TDP 371 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)371 W estimated (TDP)GPU 300 + CPU 46 + Board 25 W full load
Avg cost / hourEUR 0.11
Electricity / 1M tokensEUR 0.46
Token / kWh656.54K
Acquisition (system)EUR 6,824 full priceGPU EUR 1,400 · CPU EUR 1,399 · Board EUR 1,299 · RAM EUR 2,576 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 8,774
Output tokens (2 years)4.27B
☁️ 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 (85 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-ThinkingAMD Radeon AI PRO R9700Qwen3-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.