# LLM-Benchmark Konfiguration # Modell : Qwen3-Coder-Next # Engine : llama.cpp # Run-ID : run-20260729-032132-13812b # GPU : NVIDIA GeForce RTX 5090 # CPU : AMD Ryzen 7 5800X3D 8-Core Processor # RAM : 126 GB bench@llm-benchmark:~$ /root/llama.cpp/build/bin/llama-server \ -m /root/.cache/huggingface/hub/models--unsloth--Qwen3-Coder-Next-GGUF/snapshots/ce09c67b53bc8739eef83fe67b2f5d293c270632/Qwen3-Coder-Next-Q4_K_M.gguf \ --alias Qwen3-Coder-Next \ --host 0.0.0.0 \ --port 8000 \ -ngl 30 \ -c 16384 \ -np 4 \ --jinja

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-Next
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.	16384
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.	/root/.cache/huggingface/hub/models--unsloth--Qwen3-Coder-Next-GGUF/snapshots/ce09c67b53bc8739eef83fe67b2f5d293c270632/Qwen3-Coder-Next-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.	30
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	16384
np	4
execution_type	local

All benchmarks of this model To leaderboard

Model comparison

Qwen3-Coder-Next 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 RTX PRO 6000 Blackwell Workstation Edition 1.253,3 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.147,5 tok/sNVIDIA RTX A6000 629,8 tok/sAMD Radeon RX 7900 XTX 197,7 tok/s★ NVIDIA GeForce RTX 5090 107,0 tok/s this runNVIDIA GeForce RTX 5070 Ti 106,1 tok/sAMD Radeon AI PRO R9700 78,7 tok/sNVIDIA GeForce RTX 3090 Ti 78,2 tok/sNVIDIA DGX SPARK (GB10) 38,5 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 1.253,3 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.147,5 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 629,8 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 197,7 tok/s★ AMD Ryzen 7 5800X3D 8-Core Processor 107,0 tok/s this runAMD Ryzen Threadripper PRO 5975WX 32-Cores 106,1 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 78,2 tok/sNVIDIA Grace 38,5 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.253,3 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.147,5 tok/sDell Inc. PowerEdge R820 197,7 tok/s★ ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 107,0 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 106,1 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 78,2 tok/sASUSTeK COMPUTER INC. GX10 38,5 tok/s

ENGby engine

★ llama.cpp 1.253,3 tok/s this runvLLM 629,8 tok/sunbekannt 62,4 tok/s

DRVby driver

unbekannt 1.253,3 tok/sAMD 7.0.0-27-generic 62,4 tok/sNVIDIA 590.48.01 / CUDA 13.1 38,5 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 URL Reset

⚡ Electricity price EUR/kWh

⚙️ System utilization 100 %

🖥️ Acquisition EUR

🔌 Idle 72 W

⚡ TDP 622 W

☁️ External LLM (API) show

Input €/1M Output €/1M Input per output token

Electricity0.30 EUR/kWh

Avg power (incl. idle)622 W estimated (TDP)GPU 575 + CPU 35 + Board 12 W full load

Avg cost / hourEUR 0.19

Electricity / 1M tokensEUR 2.35

Token / kWh127.84K

Acquisition (system)EUR 4,986 full priceGPU EUR 3,300 · CPU EUR 349 · Board EUR 149 · RAM EUR 1,008 · PSU EUR 180

Electricity (2 years)–

TCO (2 years)EUR 8,253

Output tokens (2 years)1.39B

☁️ 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 (72 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-NextNVIDIA GeForce RTX 5090	Qwen3-Coder-NextNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Qwen3-Coder-Next3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition	Qwen3-Coder-Next3x 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 GeForce RTX 5090 · this run 22 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 242 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 218 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 216 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.