Contributed byMario AlkaQwen (Alibaba) Qwen3-Coder-30B-A3B-Instruct
Performance benchmark · measured on 20.08.2026 20:30
Benchmark-ID
run-20260820-205402-b9c794Timebench 3 - Kombi (Prefill + Generation)MoE30BRuntime: llama.cppQuantisierung: Q4_K_M
ℹ
For context: Diese Plattform nutzt Unified Memory – die "VRAM" ist gemeinsamer System-RAM (APU/Superchip); das Modell teilt sich den Speicher mit dem System.
Generation182,87tok/s
Prefill7.295,04tok/s
Time to First Token5.014,00ms
Total duration123,89s
Concurrency10parallel
Ranking in the field
434of 820 systems
Performance benchmark · Primary metric: Generation-Speed (tok/s) · 10× concurrent
This run is better than 47 % of all comparable systems.
Generation
182,9 tok/s
-62 % vs Ø 485,2
Prefill
7.295,0 tok/s
+56 % vs Ø 4.661,8
Time to First Token
5.014 ms
-92 % vs Ø 63.970
Distribution in the field0 – 2.491 tok/s
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-Coder-30B-A3B-Instruct this runNVIDIA GB10 · run-20260820-205402-b9c794
182,9 tok/s
How does this benchmark compare on other GPUs?
Same model on different hardware · 10× concurrent · Generation (tok/s)
NVIDIA GeForce RTX 5090run-20260729-105335-622167
1.716,6 tok/s
NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260729-032124-ef2bb1
1.690,0 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105343-8e8f9f
1.545,3 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105342-c6ca9d
1.531,9 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105342-11e651
1.455,4 tok/s
NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260724-004606-ebf474
1.070,6 tok/s
NVIDIA GeForce RTX 5090run-20260723-045450-366dae
966,2 tok/s
NVIDIA GeForce RTX 3090 Tirun-20260729-060804-8652f4
928,5 tok/s
NVIDIA GeForce RTX 3090 Tirun-20260724-004603-59220f
670,7 tok/s
2× AMD Radeon PRO W7900 Dual Slotrun-20260818-144651-c4773b
277,0 tok/s
2× AMD Radeon PRO W7900 Dual Slotrun-20260818-144651-43e6a1
258,4 tok/s
AMD Radeon PRO W7900 Dual Slotrun-20260817-133237-6a21e4
257,5 tok/s
NVIDIA GB10 this runrun-20260820-205402-b9c794
182,9 tok/s
NVIDIA GeForce RTX 5070 Tirun-20260729-032129-0b75e7
157,0 tok/s
Hardware
GPU: NVIDIA GB10 · 128 GB VRAM
CPU: NVIDIA Grace
RAM: 120 GB
Mainboard: ASUSTeK COMPUTER INC. GX10
Setup
Runtime: llama.cpp
Quantization: Q4_K_M
Driver: NVIDIA 590.48.01 / CUDA 13.1
Model: Qwen3-Coder-30B-A3B-Instruct
Configuration
# LLM-Benchmark Konfiguration
# Modell : Qwen3-Coder-30B-A3B-Instruct
# Engine : llama.cpp
# Run-ID : run-20260820-205402-b9c794
# GPU : NVIDIA GB10
# CPU : NVIDIA Grace
# RAM : 120 GB
bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \
-m Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf \
-ngl 999 \
-fa on \
-c 49152 \
-np 12
| 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. | 49152 |
| Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird. | Qwen3-Coder-30B-A3B-Instruct-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 |
| fa | on |
| Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells. | 49152 |
| np | 12 |
Anzeige
Model comparison
Qwen3-Coder-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 1.716,6 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.690,0 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.545,3 tok/sNVIDIA GeForce RTX 3090 Ti 928,5 tok/sAMD Radeon PRO W7900 Dual Slot 277,0 tok/s★ NVIDIA GB10 (DGX Spark) 182,9 tok/s this runNVIDIA GeForce RTX 5070 Ti 157,0 tok/sAMD Radeon AI PRO R9700 99,0 tok/sCPU-only 6,7 tok/s
CPUby processor
AMD Ryzen 7 5800X3D 8-Core Processor 1.716,6 tok/sAMD Ryzen 9 9950X 16-Core Processor 1.690,0 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.545,3 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 928,5 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 277,0 tok/s★ NVIDIA Grace 182,9 tok/s this runAMD Ryzen Threadripper PRO 7955WX 16-Cores 99,0 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 6,7 tok/s
MBby mainboard
ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.716,6 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.690,0 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.545,3 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 928,5 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 277,0 tok/s★ ASUSTeK COMPUTER INC. GX10 182,9 tok/s this runDell Inc. PowerEdge R820 6,7 tok/s
DRVby driver
unbekannt 1.716,6 tok/s★ NVIDIA 590.48.01 / CUDA 13.1 182,9 tok/s this runAMD 7.0.0-27-generic 88,2 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
15 W
⚡ TDP
140 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)140 W estimated (TDP)GPU 140 W full load
Avg cost / hourEUR 0.042
Electricity / 1M tokensEUR 0.064
Token / kWh4.70M
Acquisition (system)EUR 5,800 partial priceGPU EUR 4,000 · RAM EUR 1,680 · PSU EUR 120
Electricity (2 years)–
TCO (2 years)EUR 6,536
Output tokens (2 years)11.53B
☁️ 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 (15 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-Coder-30B-A3B-InstructNVIDIA GB10 (DGX Spark) | Qwen3-Coder-30B-A3B-InstructNVIDIA GeForce RTX 5090 | Qwen3-Coder-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition | Qwen3-Coder-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) | – | – | – | – |
NVIDIA GB10 (DGX Spark) · this run 183 tok/sNVIDIA GeForce RTX 5090 1,717 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 1,690 tok/s3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1,545 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.