Contributed byMario AlkaQwen (Alibaba) Qwen3-Coder-30B-A3B-Instruct
Performance benchmark · measured on 22.07.2026 23:39
Benchmark-ID
run-20260723-015519-69cce5Timebench 3 - Kombi (Prefill + Generation)MoE30BRuntime: llama.cppQuantisierung: Q4_K_M
Generation6,74tok/s
Prefill74,14tok/s
Time to First Token32.942,00ms
Total duration347,18s
Concurrency1parallel
Ranking in the field
1330of 1549 systems
Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent
This run is better than 14 % of all comparable systems.
Generation
6,7 tok/s
-91 % vs Ø 79,0
Prefill
74,1 tok/s
-97 % vs Ø 2.837,1
Time to First Token
32.942 ms
+22 % vs Ø 26.963
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-Coder-30B-A3B-Instruct this run2× NVIDIA GeForce RTX 2060 · run-20260723-015519-69cce5
6,7 tok/s
How does this benchmark compare on other GPUs?
Same model on different hardware · 1× concurrent · Generation (tok/s)
NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260729-032124-ac5167
311,3 tok/s
NVIDIA GeForce RTX 5090run-20260729-105335-497cfe
309,3 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105342-24a323
273,6 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105342-8166ac
272,2 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105342-781ac2
271,6 tok/s
NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260724-004605-d79930
237,2 tok/s
NVIDIA GeForce RTX 3090 Tirun-20260729-060804-5f5c60
198,4 tok/s
2× NVIDIA RTX A6000run-20260829-120718-30b82a
188,9 tok/s
2× NVIDIA RTX A6000run-20260830-033127-c4c7c2
173,2 tok/s
2× NVIDIA RTX A6000run-20260827-203813-6f66e2
173,1 tok/s
NVIDIA GeForce RTX 3090 Tirun-20260724-004603-963be0
171,7 tok/s
2× NVIDIA RTX A6000run-20260827-083601-26f142
164,1 tok/s
2× NVIDIA RTX A6000run-20260829-181042-2639a1
162,3 tok/s
NVIDIA RTX A6000run-20260826-054846-d66c35
161,6 tok/s
Hardware
GPU: 2x NVIDIA GeForce RTX 2060 · 6 GB VRAM
CPU: 4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz
RAM: 504 GB
Mainboard: Dell Inc. PowerEdge R820
Setup
Runtime: llama.cpp
Quantization: Q4_K_M
Model: Qwen3-Coder-30B-A3B-Instruct
Configuration
# LLM-Benchmark Konfiguration
# Modell : Qwen3-Coder-30B-A3B-Instruct
# Engine : llama.cpp
# Run-ID : run-20260723-015519-69cce5
# GPU : 2x NVIDIA GeForce RTX 2060
# CPU : 4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz
# RAM : 504 GB
bench@llm-benchmark:~$ /opt/llama.cpp/build/bin/llama-server \
-m /opt/models/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf \
-a Qwen3-Coder-30B-A3B-Instruct \
--host 0.0.0.0 \
--port 8080 \
--numa distribute \
-t 64 \
-tb 64 \
-c 8192 \
--parallel 4
| 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-Coder-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. | /opt/models/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf |
| Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen. | Qwen3-Coder-30B-A3B-Instruct |
| NUMA?NUMA-Optimierung fuer Multi-Socket-CPUs: distribute/isolate/numactl. Verbessert die Speicherlokalitaet. | distribute |
| Threads?Anzahl CPU-Threads fuer die Token-Generierung (Decode). | 64 |
| Batch-Threads?Anzahl CPU-Threads fuer Prompt-Verarbeitung und Batch (Prefill). | 64 |
| Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells. | 8192 |
| Parallel?Anzahl paralleler Slots/Sequenzen, die der Server gleichzeitig bedient. Der Kontext wird auf die Slots aufgeteilt. | 4 |
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/sNVIDIA RTX A6000 789,2 tok/sAMD Radeon PRO W7800 48GB 289,5 tok/sAMD Radeon PRO W7900 Dual Slot 277,0 tok/sNVIDIA GB10 (DGX Spark) 182,9 tok/sNVIDIA GeForce RTX 5070 Ti 157,0 tok/sAMD Radeon AI PRO R9700 99,0 tok/s★ NVIDIA GeForce RTX 2060 6,7 tok/s this run
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 7955WX 16-Cores 789,2 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 289,5 tok/sNVIDIA Grace 182,9 tok/s★ Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 6,7 tok/s this run
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 289,5 tok/sASUSTeK COMPUTER INC. GX10 182,9 tok/s★ Dell Inc. PowerEdge R820 6,7 tok/s this run
DRVby driver
unbekannt 1.716,6 tok/sNVIDIA 590.48.01 / CUDA 13.1 182,9 tok/sAMD 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 (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
55 W
⚡ TDP
359 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)359 W estimated (TDP)GPU 320 + CPU 29 + Board 10 W full load
Avg cost / hourEUR 0.11
Electricity / 1M tokensEUR 4.44
Token / kWh67.63K
Acquisition (system)EUR 2,425 partial priceGPU EUR 220 · CPU EUR 39 · RAM EUR 2,016 · PSU EUR 150
Electricity (2 years)–
TCO (2 years)EUR 4,311
Output tokens (2 years)425.11M
☁️ 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 (55 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-Instruct2x NVIDIA GeForce RTX 2060 | Qwen3-Coder-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition | Qwen3-Coder-30B-A3B-InstructNVIDIA GeForce RTX 5090 | 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) | – | – | – | – |
2× NVIDIA GeForce RTX 2060 · this run 7 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 311 tok/sNVIDIA GeForce RTX 5090 309 tok/s3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 274 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.