# LLM-Benchmark Konfiguration # Modell : Qwen2.5-Coder-32B-Instruct # Engine : llama.cpp # Run-ID : run-20260730-181639-2718a6 # 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--bartowski--Qwen2.5-Coder-32B-Instruct-GGUF/snapshots/40b525506a4f98ed425882fa6dfc90cc8139065e/Qwen2.5-Coder-32B-Instruct-Q4_K_M.gguf \ --alias Qwen2.5-Coder-32B-Instruct \ --host 0.0.0.0 \ --port 8000 \ -ngl 999 \ -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.	Qwen2.5-Coder-32B-Instruct
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--bartowski--Qwen2.5-Coder-32B-Instruct-GGUF/snapshots/40b525506a4f98ed425882fa6dfc90cc8139065e/Qwen2.5-Coder-32B-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
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	16384
np	4

All benchmarks of this model To leaderboard

Model comparison

Qwen2.5-Coder-32B-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 RTX PRO 6000 Blackwell Workstation Edition 500,6 tok/s★ NVIDIA GeForce RTX 5090 479,6 tok/s this runNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 412,8 tok/sNVIDIA GeForce RTX 3090 Ti 236,4 tok/sAMD Radeon AI PRO R9700 63,2 tok/sNVIDIA GeForce RTX 5070 Ti 45,3 tok/sAMD Radeon 8060S Graphics 20,6 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 500,6 tok/s★ AMD Ryzen 7 5800X3D 8-Core Processor 479,6 tok/s this runAMD Ryzen Threadripper PRO 9965WX 24-Cores 412,8 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 236,4 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 63,2 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 45,3 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 20,6 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 500,6 tok/s★ ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 479,6 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 412,8 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 236,4 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 45,3 tok/sBosgame AXB35-02 (BeyondMax Series) 20,6 tok/s

ENGby engine

vLLM 500,6 tok/s★ llama.cpp 479,6 tok/s this run

DRVby driver

unbekannt 500,6 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 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 0.22

Token / kWh1.34M

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)14.63B

☁️ 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

	Qwen2.5-Coder-32B-InstructNVIDIA GeForce RTX 5090	Qwen2.5-Coder-32B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Qwen2.5-Coder-32B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Qwen2.5-Coder-32B-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 GeForce RTX 5090 · this run 232 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 298 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 256 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 218 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.