# LLM-Benchmark Konfiguration # Modell : Codestral-22B-v0.1 # Engine : llama.cpp # Run-ID : run-20260817-212318-7fe056 # GPU : AMD Radeon PRO W7900 Dual Slot # CPU : AMD Ryzen Threadripper PRO 5975WX 32-Cores # RAM : 247 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build_hip/bin/llama-server \ -m /mnt/llm/gguf/Codestral-22B-v0.1-Q4_K_M/Codestral-22B-v0.1-IQ4_XS.gguf \ --alias Codestral-22B-v0.1 \ -ngl 999 \ -fa on \ -c 49152 \ -np 12 \ --jinja \ --host 0.0.0.0 \ --port 8000

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.	Codestral-22B-v0.1
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.	/mnt/llm/gguf/Codestral-22B-v0.1-Q4_K_M/Codestral-22B-v0.1-IQ4_XS.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

All benchmarks of this model To leaderboard

Model comparison

Codestral-22B-v0.1 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 641,4 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 629,5 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 559,4 tok/sNVIDIA GeForce RTX 3090 Ti 325,2 tok/sAMD Radeon AI PRO R9700 201,5 tok/s★ AMD Radeon PRO W7900 Dual Slot 147,5 tok/s this runNVIDIA GB10 (DGX Spark) 80,0 tok/sNVIDIA GeForce RTX 5070 Ti 62,9 tok/sIntel Arc Pro B70 23,6 tok/sNVIDIA Tesla P100 PCIe 16GB 22,2 tok/s

CPUby processor

AMD Ryzen 7 5800X3D 8-Core Processor 641,4 tok/sAMD Ryzen 9 9950X 16-Core Processor 629,5 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 559,4 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 325,2 tok/sAMD Ryzen 5 5600X 6-Core Processor 277,9 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 201,5 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 147,5 tok/s this runAMD Ryzen 9 7945HX with Radeon Graphics 23,6 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 641,4 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 629,5 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 559,4 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 325,2 tok/sASUSTeK COMPUTER INC. PRIME A520M-K 277,9 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 147,5 tok/s this rununbekannt 80,0 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 23,6 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd F1FXM (DeskMini Series) 22,2 tok/s

ENGby engine

★ llama.cpp 641,4 tok/s this runvLLM 277,9 tok/sunbekannt 214,1 tok/s

DRVby driver

unbekannt 641,4 tok/sNVIDIA 580.159.03 / CUDA 13.0 80,0 tok/sAMD 7.0.0-27-generic 33,5 tok/sIntel 26.18.38308.4 23,6 tok/s

💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (10× 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 10 W

⚡ TDP 305 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)305 W estimated (TDP)GPU 295 + Board 10 W full load

Avg cost / hourEUR 0.092

Electricity / 1M tokensEUR 0.19

Token / kWh1.59M

Acquisition (system)EUR 2,126 missingRAM EUR 1,976 · PSU EUR 150

Electricity (2 years)–

TCO (2 years)EUR 3,729

Output tokens (2 years)8.48B

☁️ 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 (10 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

	Codestral-22B-v0.1AMD Radeon PRO W7900 Dual Slot	Codestral-22B-v0.1NVIDIA GeForce RTX 5090	Codestral-22B-v0.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition	Codestral-22B-v0.13x 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)	–	–	–	–

AMD Radeon PRO W7900 Dual Slot · this run 135 tok/s NVIDIA GeForce RTX 5090 641 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 629 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 559 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.