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

Qwen3-30B-A3B-Thinking-2507

Performance benchmark · measured on 28.08.2026 09:22

Benchmark-IDrun-20260828-073525-6662bf
Timebench 3 - Kombi (Prefill + Generation)MoE30BRuntime: llama.cppQuantisierung: Q8_0
Generation425,16tok/s
Prefill13.041,17tok/s
Time to First Token8.250,50ms
Total duration92,41s
Concurrency10parallel
Ranking in the field
373of 1026 systems

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

This run is better than 64 % of all comparable systems.
Generation 425,2 tok/s
-8 % vs Ø 461,9
Prefill 13.041,2 tok/s
+119 % vs Ø 5.941,8
Time to First Token 8.251 ms
-84 % vs Ø 52.987
Distribution in the field0 – 2.491 tok/s
Ø 462 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-e28775
2.491,2 tok/s
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
gemma-4-E2B-it3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-d87c73
2.143,6 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-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-0aed86
1.937,7 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-8db0fa
1.911,6 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-e0eafd
1.897,0 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-7c961d
1.890,7 tok/s
Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-2ed9dd
1.878,7 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-034052-26063b
1.835,7 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-a77046
1.830,3 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-c6e7e0
1.819,5 tok/s
Qwen3-30B-A3B-Thinking-2507 this run2× NVIDIA RTX A6000 · run-20260828-073525-6662bf
425,2 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: 2x NVIDIA RTX A6000 · 48 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: Q8_0
Model: Qwen3-30B-A3B-Thinking-2507

Configuration

benchmark-konfiguration — run-20260828-073525-6662bf
# LLM-Benchmark Konfiguration # Modell : Qwen3-30B-A3B-Thinking-2507 # Engine : llama.cpp # Run-ID : run-20260828-073525-6662bf # GPU : 2x NVIDIA RTX A6000 # CPU : AMD Ryzen Threadripper PRO 7955WX 16-Cores # RAM : 184 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m Qwen_Qwen3-30B-A3B-Thinking-2507-Q8_0.gguf \ -ngl 999 \ -fa on \ -c 32768 \ -np 8 \ -sm layer '(2x' RTX A6000 '48GB)'
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
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.32768
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.Qwen_Qwen3-30B-A3B-Thinking-2507-Q8_0.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
faon
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.32768
np8
Split-Mode?Verteilung ueber mehrere GPUs: none (nur eine GPU), layer (Layer aufteilen) oder row (Tensoren zeilenweise).layer

All benchmarks of this model To leaderboard

Anzeige
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

2.1871.6401.0945470,007.58515.17022.756Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 5090 - 1.683,8 tok/s Generation, 14.349 tok/s Prefill, TTFT 2.214 ms (6 Laufe)NVIDIA GeForce RTX 50...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.670,5 tok/s Generation, 18.362 tok/s Prefill, TTFT 1.942 ms (6 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 1.521,4 tok/s Generation, 10.574 tok/s Prefill, TTFT 3.521 ms (9 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 Ti - 930,6 tok/s Generation, 7.726 tok/s Prefill, TTFT 5.880 ms (6 Laufe)NVIDIA GeForce RTX 30...AMD Radeon PRO W7900 Dual Slot - 254,6 tok/s Generation, 4.711 tok/s Prefill, TTFT 2.915 ms (6 Laufe)AMD Radeon PRO W7900 ...NVIDIA GeForce RTX 5070 Ti - 155,8 tok/s Generation, 1.078 tok/s Prefill, TTFT 23.667 ms (6 Laufe)NVIDIA GeForce RTX 50...AMD Radeon AI PRO R9700 - 91,4 tok/s Generation, 2.676 tok/s Prefill, TTFT 39.171 ms (25 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 2060 - 8,5 tok/s Generation, 74 tok/s Prefill, TTFT 134.321 ms (3 Laufe)NVIDIA GeForce RTX 20...NVIDIA RTX A6000 - 673,2 tok/s Generation, 13.458 tok/s Prefill, TTFT 1.574 ms (24 Laufe) | DIESER LAUF★ NVIDIA RTX A6000
NVIDIA GeForce RTX 5090 1.683,8 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.670,5 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.521,4 tok/sNVIDIA GeForce RTX 3090 Ti 930,6 tok/s★ NVIDIA RTX A6000 673,2 tok/s this runAMD Radeon PRO W7900 Dual Slot 254,6 tok/sNVIDIA GeForce RTX 5070 Ti 155,8 tok/sAMD Radeon AI PRO R9700 91,4 tok/sNVIDIA GeForce RTX 2060 8,5 tok/s

CPUby processor

2.1871.6401.0945470,007.58515.17022.756Prefill (tok/s)Generation (tok/s)AMD Ryzen 7 5800X3D 8-Core Processor - 1.683,8 tok/s Generation, 14.349 tok/s Prefill, TTFT 2.214 ms (6 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen 9 9950X 16-Core Processor - 1.670,5 tok/s Generation, 18.362 tok/s Prefill, TTFT 1.942 ms (6 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 1.521,4 tok/s Generation, 10.574 tok/s Prefill, TTFT 3.521 ms (9 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 930,6 tok/s Generation, 7.726 tok/s Prefill, TTFT 5.880 ms (6 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 254,6 tok/s Generation, 2.894 tok/s Prefill, TTFT 13.291 ms (12 Laufe)AMD Ryzen Threadrippe...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 Threadripper PRO 7955WX 16-Cores - 673,2 tok/s Generation, 7.957 tok/s Prefill, TTFT 20.756 ms (49 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 7 5800X3D 8-Core Processor 1.683,8 tok/sAMD Ryzen 9 9950X 16-Core Processor 1.670,5 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.521,4 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 930,6 tok/s★ AMD Ryzen Threadripper PRO 7955WX 16-Cores 673,2 tok/s this runAMD Ryzen Threadripper PRO 5975WX 32-Cores 254,6 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 8,5 tok/s

MBby mainboard

2.1871.6401.0945470,007.58515.17022.756Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 1.683,8 tok/s Generation, 14.349 tok/s Prefill, TTFT 2.214 ms (6 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 1.670,5 tok/s Generation, 18.362 tok/s Prefill, TTFT 1.942 ms (6 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 930,6 tok/s Generation, 7.726 tok/s Prefill, TTFT 5.880 ms (6 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 254,6 tok/s Generation, 2.894 tok/s Prefill, TTFT 13.291 ms (12 Laufe)ASUSTeK COMPUTER INC....Dell Inc. PowerEdge R820 - 8,5 tok/s Generation, 74 tok/s Prefill, TTFT 134.321 ms (3 Laufe)Dell Inc. PowerEdge R...ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 1.521,4 tok/s Generation, 8.363 tok/s Prefill, TTFT 18.082 ms (58 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.683,8 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.670,5 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.521,4 tok/s this runMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 930,6 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 254,6 tok/sDell Inc. PowerEdge R820 8,5 tok/s

ENGby engine

2.1711.6281.0855430,01.3976.54811.70016.852Prefill (tok/s)Generation (tok/s)vLLM - 906,0 tok/s Generation, 14.181 tok/s Prefill, TTFT 2.688 ms (29 Laufe)vLLMunbekannt - 91,4 tok/s Generation, 4.068 tok/s Prefill, TTFT 1.364 ms (8 Laufe)unbekanntllama.cpp - 1.683,8 tok/s Generation, 5.905 tok/s Prefill, TTFT 29.307 ms (54 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 1.683,8 tok/s this runvLLM 906,0 tok/sunbekannt 91,4 tok/s

DRVby driver

2.1711.6281.0855430,02.6895.1847.68010.175Prefill (tok/s)Generation (tok/s)unbekannt - 1.683,8 tok/s Generation, 8.796 tok/s Prefill, TTFT 20.006 ms (83 Laufe)unbekanntAMD 7.0.0-27-generic - 91,4 tok/s Generation, 4.068 tok/s Prefill, TTFT 1.364 ms (8 Laufe)AMD 7.0.0-27-generic
unbekannt 1.683,8 tok/sAMD 7.0.0-27-generic 91,4 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 95 W
⚡ TDP 671 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)671 W estimated (TDP)GPU 600 + CPU 46 + Board 25 W full load
Avg cost / hourEUR 0.20
Electricity / 1M tokensEUR 0.13
Token / kWh2.28M
Acquisition (system)EUR 11,454 full priceGPU EUR 6,000 · CPU EUR 1,399 · Board EUR 1,299 · RAM EUR 2,576 · PSU EUR 180
Electricity (2 years)
TCO (2 years)EUR 14,981
Output tokens (2 years)26.82B
☁️ 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 (95 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

Qwen3-30B-A3B-Thinking-25072x NVIDIA RTX A6000Qwen3-30B-A3B-Thinking-2507NVIDIA GeForce RTX 5090Qwen3-30B-A3B-Thinking-2507NVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen3-30B-A3B-Thinking-25073x 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.