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

Qwen3-Coder-30B-A3B-Instruct

Performance benchmark · measured on 25.09.2026 14:17

Benchmark-IDrun-20260925-123443-cd61da
Timebench 3 - Kombi (Prefill + Generation)MoE30BRuntime: llama.cppQuantisierung: Q4_K_M
Generation400,42tok/s
Prefill12.694,05tok/s
Time to First Token1.086,00ms
Total duration27,83s
Concurrency5parallel
Ranking in the field
1of 1 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 5× concurrent

This run is better than 100 % of all comparable systems.
Generation 400,4 tok/s
+0 % vs Ø 400,4
Prefill 12.694,1 tok/s
+0 % vs Ø 12.694,1
Time to First Token 1.086 ms
+0 % vs Ø 1.086

Wie schlägt sich dieser Benchmark mit anderen Modellen?

How does this benchmark compare on other GPUs?

Same model on different hardware · 5× concurrent · Generation (tok/s)

Hardware

GPU: NVIDIA GeForce RTX 4090 · 24 GB VRAM
CPU: AMD Ryzen 3 3100 4-Core Processor
RAM: 61 GB
Mainboard: Micro-Star International Co., Ltd. B550M PRO-VDH WIFI (MS-7C95)

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Qwen3-Coder-30B-A3B-Instruct

Configuration

benchmark-konfiguration — run-20260925-123443-cd61da
# LLM-Benchmark Konfiguration # Modell : Qwen3-Coder-30B-A3B-Instruct # Engine : llama.cpp # Run-ID : run-20260925-123443-cd61da # GPU : NVIDIA GeForce RTX 4090 # CPU : AMD Ryzen 3 3100 4-Core Processor # RAM : 61 GB bench@llm-benchmark:~$ /home/godcore/benchmark/llama-b11178/llama-b11178/llama-server \ -m /mnt/llm/gguf/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf \ --alias Qwen3-Coder-30B-A3B-Instruct \ --host 0.0.0.0 \ --port 8000 \ -ngl 99 \ -c 20480 \ -np 5 \ -fa on \ -ctk q8_0 \ -ctv q8_0
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.4096
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird./mnt/llm/gguf/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M/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.99
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.20480
np5
faon
ctkq8_0
ctvq8_0
CUDA_VISIBLE_DEVICES0

All benchmarks of this model To leaderboard

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

2.2301.6731.1155580,006.87513.75020.625Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 5090 - 1.716,6 tok/s Generation, 15.919 tok/s Prefill, TTFT 2.829 ms (4 Laufe)NVIDIA GeForce RTX 50...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.690,0 tok/s Generation, 16.648 tok/s Prefill, TTFT 1.846 ms (6 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 1.545,3 tok/s Generation, 13.495 tok/s Prefill, TTFT 3.236 ms (9 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 Ti - 928,5 tok/s Generation, 9.749 tok/s Prefill, TTFT 3.637 ms (6 Laufe)NVIDIA GeForce RTX 30...NVIDIA RTX A6000 - 789,2 tok/s Generation, 14.630 tok/s Prefill, TTFT 1.638 ms (36 Laufe)NVIDIA RTX A6000AMD Radeon RX 7900 XTX - 324,9 tok/s Generation, 5.606 tok/s Prefill, TTFT 2.364 ms (3 Laufe)AMD Radeon RX 7900 XTXAMD Radeon PRO W7800 48GB - 289,5 tok/s Generation, 6.568 tok/s Prefill, TTFT 2.348 ms (6 Laufe)AMD Radeon PRO W7800 ...AMD Radeon PRO W7900 Dual Slot - 277,0 tok/s Generation, 4.441 tok/s Prefill, TTFT 3.159 ms (9 Laufe)AMD Radeon PRO W7900 ...AMD Radeon AI PRO R9700 - 250,2 tok/s Generation, 3.358 tok/s Prefill, TTFT 29.901 ms (30 Laufe)AMD Radeon AI PRO R97...NVIDIA GB10 (DGX Spark) - 182,9 tok/s Generation, 4.998 tok/s Prefill, TTFT 2.913 ms (3 Laufe)NVIDIA GB10 (DGX Spar...NVIDIA GeForce RTX 5070 Ti - 157,0 tok/s Generation, 1.323 tok/s Prefill, TTFT 32.375 ms (3 Laufe)NVIDIA GeForce RTX 50...CPU-only - 6,7 tok/s Generation, 103 tok/s Prefill, TTFT 107.342 ms (3 Laufe)CPU-onlyNVIDIA GeForce RTX 4090 - 400,4 tok/s Generation, 9.941 tok/s Prefill, TTFT 712 ms (2 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 40...
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/s★ NVIDIA GeForce RTX 4090 400,4 tok/s this runAMD Radeon RX 7900 XTX 324,9 tok/sAMD Radeon PRO W7800 48GB 289,5 tok/sAMD Radeon PRO W7900 Dual Slot 277,0 tok/sAMD Radeon AI PRO R9700 250,2 tok/sNVIDIA GB10 (DGX Spark) 182,9 tok/sNVIDIA GeForce RTX 5070 Ti 157,0 tok/sCPU-only 6,7 tok/s

CPUby processor

2.2301.6731.1155580,006.87513.75020.625Prefill (tok/s)Generation (tok/s)AMD Ryzen 7 5800X3D 8-Core Processor - 1.716,6 tok/s Generation, 15.919 tok/s Prefill, TTFT 2.829 ms (4 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen 9 9950X 16-Core Processor - 1.690,0 tok/s Generation, 16.648 tok/s Prefill, TTFT 1.846 ms (6 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 1.545,3 tok/s Generation, 13.495 tok/s Prefill, TTFT 3.236 ms (9 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 928,5 tok/s Generation, 9.749 tok/s Prefill, TTFT 3.637 ms (6 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 789,2 tok/s Generation, 9.690 tok/s Prefill, TTFT 15.059 ms (63 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 3955WX 16-Cores - 324,9 tok/s Generation, 5.606 tok/s Prefill, TTFT 2.364 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 289,5 tok/s Generation, 4.630 tok/s Prefill, TTFT 7.758 ms (18 Laufe)AMD Ryzen Threadrippe...NVIDIA Grace - 182,9 tok/s Generation, 4.998 tok/s Prefill, TTFT 2.913 ms (3 Laufe)NVIDIA GraceIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 6,7 tok/s Generation, 103 tok/s Prefill, TTFT 107.342 ms (3 Laufe)Intel(R) Xeon(R) CPU ...AMD Ryzen 3 3100 4-Core Processor - 400,4 tok/s Generation, 7.361 tok/s Prefill, TTFT 1.734 ms (5 Laufe) | DIESER LAUF★ AMD Ryzen 3 3100 4-Co...
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/s★ AMD Ryzen 3 3100 4-Core Processor 400,4 tok/s this runAMD Ryzen Threadripper PRO 3955WX 16-Cores 324,9 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 289,5 tok/sNVIDIA Grace 182,9 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 6,7 tok/s

MBby mainboard

2.2301.6731.1155580,006.87513.75020.625Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 1.716,6 tok/s Generation, 15.919 tok/s Prefill, TTFT 2.829 ms (4 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 1.690,0 tok/s Generation, 16.648 tok/s Prefill, TTFT 1.846 ms (6 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 1.545,3 tok/s Generation, 10.166 tok/s Prefill, TTFT 13.581 ms (72 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 928,5 tok/s Generation, 9.749 tok/s Prefill, TTFT 3.637 ms (6 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 324,9 tok/s Generation, 4.770 tok/s Prefill, TTFT 6.987 ms (21 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING - 250,2 tok/s Generation, 5.641 tok/s Prefill, TTFT 2.415 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. GX10 - 182,9 tok/s Generation, 4.998 tok/s Prefill, TTFT 2.913 ms (3 Laufe)ASUSTeK COMPUTER INC....Dell Inc. PowerEdge R820 - 6,7 tok/s Generation, 103 tok/s Prefill, TTFT 107.342 ms (3 Laufe)Dell Inc. PowerEdge R...Micro-Star International Co., Ltd. B550M PRO-VDH WIFI (MS-7C95) - 400,4 tok/s Generation, 9.941 tok/s Prefill, TTFT 712 ms (2 Laufe) | DIESER LAUF★ Micro-Star Internatio...
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/s★ Micro-Star International Co., Ltd. B550M PRO-VDH WIFI (MS-7C95) 400,4 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 324,9 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 250,2 tok/sASUSTeK COMPUTER INC. GX10 182,9 tok/sDell Inc. PowerEdge R820 6,7 tok/s

ENGby engine

2.2141.6601.1075530,01.2397.41713.59419.772Prefill (tok/s)Generation (tok/s)vLLM - 1.070,6 tok/s Generation, 16.587 tok/s Prefill, TTFT 955 ms (33 Laufe)vLLMunbekannt - 88,2 tok/s Generation, 4.424 tok/s Prefill, TTFT 938 ms (9 Laufe)unbekanntllama.cpp - 1.716,6 tok/s Generation, 6.655 tok/s Prefill, TTFT 18.824 ms (78 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 1.716,6 tok/s this runvLLM 1.070,6 tok/sunbekannt 88,2 tok/s

DRVby driver

2.2141.6601.1075530,02.8835.6818.47911.276Prefill (tok/s)Generation (tok/s)unbekannt - 1.716,6 tok/s Generation, 9.736 tok/s Prefill, TTFT 13.806 ms (108 Laufe)unbekanntNVIDIA 590.48.01 / CUDA 13.1 - 182,9 tok/s Generation, 4.998 tok/s Prefill, TTFT 2.913 ms (3 Laufe)NVIDIA 590.48.01 / CU...AMD 7.0.0-27-generic - 88,2 tok/s Generation, 4.424 tok/s Prefill, TTFT 938 ms (9 Laufe)AMD 7.0.0-27-generic
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 (5× 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 0 W
⚡ TDP 450 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)450 W estimated (TDP)GPU 450 W full load
Avg cost / hourEUR 0.14
Electricity / 1M tokensEUR 0.094
Token / kWh3.20M
Acquisition (system)EUR 2,150 partial priceGPU EUR 2,000 · PSU EUR 150
Electricity (2 years)–
TCO (2 years)EUR 4,515
Output tokens (2 years)25.26B
☁️ 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 (0 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 GeForce RTX 4090Qwen3-Coder-30B-A3B-InstructNVIDIA GeForce RTX 5090Qwen3-Coder-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen3-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)––––

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.