Contributed byMario AlkaQwen (Alibaba) Qwen3-VL-30B-A3B-Instruct
Performance benchmark · measured on 21.07.2026 15:25
Benchmark-ID
run-20260722-165906-06e2ccMoE30BRuntime: godclaw
Generation89,84tok/s
Prefill4.030,61tok/s
Time to First Token605,00ms
Total duration24,01s
Concurrency1parallel
Ranking in the field
295of 1161 systems
Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent
This run is better than 75 % of all comparable systems.
Generation
89,8 tok/s
+21 % vs Ø 74,3
Prefill
4.030,6 tok/s
+73 % vs Ø 2.324,7
Time to First Token
605 ms
-98 % vs Ø 35.657
Distribution in the field0 – 405 tok/s
Wie schlägt sich dieser Benchmark mit anderen Modellen?
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004608-16af9b
404,6 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-9f766a
395,2 tok/s
Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-d456e7
393,5 tok/s
Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-bffb11
393,5 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004607-29bd16
388,9 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-1c779f
388,2 tok/s
gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-6ea089
378,6 tok/s
gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-e8b129
377,6 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-ac388e
362,3 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-5e5085
361,4 tok/s
Nemotron-3-Nano-30B-A3BNVIDIA GeForce RTX 5090 · run-20260729-105335-653788
359,4 tok/s
Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA GeForce RTX 5090 · run-20260729-105334-2c4905
359,3 tok/s
Nemotron-Cascade-2-30B-A3BNVIDIA GeForce RTX 5090 · run-20260729-105334-44d1e7
359,0 tok/s
Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032119-4852bf
357,1 tok/s
Qwen3-VL-30B-A3B-Instruct this run3× AMD Radeon AI PRO R9700 · run-20260722-165906-06e2cc
89,8 tok/s
How does this benchmark compare on other GPUs?
Same model on different hardware · 1× concurrent · Generation (tok/s)
NVIDIA GeForce RTX 5090run-20260729-105336-32f876
307,4 tok/s
NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260729-032125-021dfb
303,6 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105343-0df3c1
269,1 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105343-d6b1eb
268,2 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-122848-9ce6f1
262,1 tok/s
NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260724-004607-ae055d
227,9 tok/s
NVIDIA GeForce RTX 3090 Tirun-20260729-105331-79f292
197,7 tok/s
2× AMD Radeon PRO W7900 Dual Slotrun-20260818-151857-5183f0
98,0 tok/s
3× AMD Radeon AI PRO R9700 this runrun-20260722-165906-06e2cc
89,8 tok/s
3× AMD Radeon AI PRO R9700run-20260722-165906-44e9fd
86,8 tok/s
3× AMD Radeon AI PRO R9700run-20260722-165906-69e645
86,7 tok/s
3× AMD Radeon AI PRO R9700run-20260722-165906-072c98
69,2 tok/s
3× AMD Radeon AI PRO R9700run-20260722-165904-d6004e
69,2 tok/s
NVIDIA GeForce RTX 5070 Tirun-20260729-032130-17e475
63,1 tok/s
Hardware
GPU: 3x AMD Radeon AI PRO R9700 · 32 GB VRAM
CPU: 32x AMD Ryzen Threadripper PRO 7955WX 16-Cores
RAM: 184 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE
Setup
Runtime: godclaw
Quantization: -
Operating system: Ubuntu 26.04 LTS (Kernel 7.0.0-27-generic)
Driver: AMD 7.0.0-27-generic
Model: Qwen3-VL-30B-A3B-Instruct
Anmerkung
llama.cpp . 2 GPU . GGUF (unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF)
Configuration
# LLM-Benchmark Konfiguration
# Modell : Qwen3-VL-30B-A3B-Instruct
# Run-ID : run-20260722-165906-06e2cc
# GPU : 3x AMD Radeon AI PRO R9700
# CPU : 32x AMD Ryzen Threadripper PRO 7955WX 16-Cores
# RAM : 184 GB
bench@llm-benchmark:~$ cat benchmark.conf
Konfigurationspfad unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF
Engine llamacpp
Modellalias Qwen3-VL-30B-A3B-Instruct
Kontextlaenge 8192
GPU-Layer 999
Host 0.0.0.0
Port 8000
Split-Mode layer
| 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-VL-30B-A3B-Instruct |
| Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann. | 8192 |
| Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird. | unsloth/Qwen3-VL-30B-A3B-Instruct-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. | 8192 |
| Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen. | Qwen3-VL-30B-A3B-Instruct |
| Host?Netzwerk-Interface, an das der HTTP-Server bindet, z.B. 0.0.0.0 fuer alle Interfaces. | 0.0.0.0 |
| Port?TCP-Port des HTTP-Servers. | 8000 |
| Split-Mode?Verteilung ueber mehrere GPUs: none (nur eine GPU), layer (Layer aufteilen) oder row (Tensoren zeilenweise). | layer |
Anzeige
Videoreihe und Benchmarkauswertung zur AMD R9700
Model comparison
Qwen3-VL-30B-A3B-Instruct 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
NVIDIA GeForce RTX 5090 1.655,9 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.639,0 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.505,0 tok/sNVIDIA GeForce RTX 3090 Ti 903,5 tok/sAMD Radeon PRO W7900 Dual Slot 245,1 tok/sNVIDIA GeForce RTX 5070 Ti 154,0 tok/s★ AMD Radeon AI PRO R9700 89,8 tok/s this run
CPUby processor
AMD Ryzen 7 5800X3D 8-Core Processor 1.655,9 tok/sAMD Ryzen 9 9950X 16-Core Processor 1.639,0 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.505,0 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 903,5 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 245,1 tok/s★ AMD Ryzen Threadripper PRO 7955WX 16-Cores 89,8 tok/s this run
MBby mainboard
ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.655,9 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.639,0 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.505,0 tok/s this runMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 903,5 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 245,1 tok/s
DRVby driver
unbekannt 1.655,9 tok/s★ AMD 7.0.0-27-generic 89,8 tok/s this run
💰 Economics
Economics of this run
Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (1× 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
125 W
⚡ TDP
971 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)971 W estimated (TDP)GPU 900 + CPU 46 + Board 25 W full load
Avg cost / hourEUR 0.29
Electricity / 1M tokensEUR 0.90
Token / kWh333.08K
Acquisition (system)EUR 9,674 full priceGPU EUR 4,200 · CPU EUR 1,399 · Board EUR 1,299 · RAM EUR 2,576 · PSU EUR 200
Electricity (2 years)–
TCO (2 years)EUR 14,778
Output tokens (2 years)5.67B
☁️ 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 (125 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-VL-30B-A3B-Instruct3x AMD Radeon AI PRO R9700 | Qwen3-VL-30B-A3B-InstructNVIDIA GeForce RTX 5090 | Qwen3-VL-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition | Qwen3-VL-30B-A3B-Instruct3x 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) | – | – | – | – |
3× AMD Radeon AI PRO R9700 · this run 90 tok/sNVIDIA GeForce RTX 5090 307 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 304 tok/s3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 269 tok/s
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.