Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
Contributed byMario AlkaMistral AI

Codestral-22B-v0.1

Performance benchmark · measured on 29.07.2026 06:59

Benchmark-IDrun-20260729-105333-d7ef15
Timebench 3 - Kombi (Prefill + Generation)Dense22BRuntime: llama.cppQuantisierung: Q4_K_M
Generation346,65tok/s
Prefill6.718,83tok/s
Time to First Token4.938,00ms
Total duration55,69s
Concurrency5parallel
Ranking in the field
30of 44 systems

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

This run is better than 33 % of all comparable systems.
Generation 346,7 tok/s
-42 % vs Ø 599,2
Prefill 6.718,8 tok/s
-8 % vs Ø 7.302,3
Time to First Token 4.938 ms
-79 % vs Ø 23.290
Distribution in the field2 – 1.302 tok/s
Ø 599 Median Dieser Lauf

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 5090 · 32 GB VRAM
CPU: AMD Ryzen 7 5800X3D 8-Core Processor
RAM: 126 GB
Mainboard: ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Codestral-22B-v0.1

Configuration

benchmark-konfiguration — run-20260729-105333-d7ef15
# LLM-Benchmark Konfiguration # Modell : Codestral-22B-v0.1 # Engine : llama.cpp # Run-ID : run-20260729-105333-d7ef15 # 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--Codestral-22B-v0.1-GGUF/snapshots/0e6abe14d6aeaf2c99d5dc9973205e8e38692d90/Codestral-22B-v0.1-Q4_K_M.gguf \ --alias Codestral-22B-v0.1 \ --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.Codestral-22B-v0.1
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--Codestral-22B-v0.1-GGUF/snapshots/0e6abe14d6aeaf2c99d5dc9973205e8e38692d90/Codestral-22B-v0.1-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
np4

All benchmarks of this model To leaderboard

Anzeige
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

8216164112050,002.6115.2217.832Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 629,5 tok/s Generation, 5.700 tok/s Prefill, TTFT 6.905 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 559,4 tok/s Generation, 6.460 tok/s Prefill, TTFT 8.205 ms (9 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 Ti - 325,2 tok/s Generation, 2.907 tok/s Prefill, TTFT 14.580 ms (3 Laufe)NVIDIA GeForce RTX 30...NVIDIA GeForce RTX 5070 Ti - 62,9 tok/s Generation, 994 tok/s Prefill, TTFT 64.942 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA GeForce RTX 5090 - 641,4 tok/s Generation, 5.824 tok/s Prefill, TTFT 7.096 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
★ NVIDIA GeForce RTX 5090 641,4 tok/s this runNVIDIA 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/sNVIDIA GeForce RTX 5070 Ti 62,9 tok/s

CPUby processor

8216164112050,002.6115.2217.832Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 629,5 tok/s Generation, 5.700 tok/s Prefill, TTFT 6.905 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 559,4 tok/s Generation, 6.460 tok/s Prefill, TTFT 8.205 ms (9 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 325,2 tok/s Generation, 2.907 tok/s Prefill, TTFT 14.580 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 62,9 tok/s Generation, 994 tok/s Prefill, TTFT 64.942 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 7 5800X3D 8-Core Processor - 641,4 tok/s Generation, 5.824 tok/s Prefill, TTFT 7.096 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 7 5800X3D 8...
★ AMD Ryzen 7 5800X3D 8-Core Processor 641,4 tok/s this runAMD 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 Threadripper PRO 5975WX 32-Cores 62,9 tok/s

MBby mainboard

8216164112050,002.6115.2217.832Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 629,5 tok/s Generation, 5.700 tok/s Prefill, TTFT 6.905 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 559,4 tok/s Generation, 6.460 tok/s Prefill, TTFT 8.205 ms (9 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 325,2 tok/s Generation, 2.907 tok/s Prefill, TTFT 14.580 ms (3 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 62,9 tok/s Generation, 994 tok/s Prefill, TTFT 64.942 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 641,4 tok/s Generation, 5.824 tok/s Prefill, TTFT 7.096 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 641,4 tok/s this runASUSTeK 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. Pro WS WRX80E-SAGE SE WIFI 62,9 tok/s

ENGby engine

7066736416095774.6744.8735.0715.270Prefill (tok/s)Generation (tok/s)llama.cpp - 641,4 tok/s Generation, 4.972 tok/s Prefill, TTFT 16.877 ms (21 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 641,4 tok/s this run

DRVby driver

7066736416095774.6744.8735.0715.270Prefill (tok/s)Generation (tok/s)unbekannt - 641,4 tok/s Generation, 4.972 tok/s Prefill, TTFT 16.877 ms (21 Laufe)unbekannt
unbekannt 641,4 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 72 W
⚡ TDP 622 W
☁️ External LLM (API)
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 0.15
Token / kWh2.01M
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)21.86B
☁️ 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

Codestral-22B-v0.1NVIDIA GeForce RTX 5090Codestral-22B-v0.1NVIDIA RTX PRO 6000 Blackwell Workstation EditionCodestral-22B-v0.13x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionCodestral-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)

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.