codestral:latest

llama · 22.2B · Q4_0

Gigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4 (Intel Core™ i5-14400F)

32 GB · Microsoft Windows 11 Professionnel 10.0.26200

Tested on September 15, 2026 · Submitted by ichido

Top 52% Compare

Global Score

76 /100

Good

Hardware Fit

91/100

Quality

69/100

Get this model

🦙

Ollama

ollama pull codestral:latest

View on Ollama Library

ollama.com/library/codestral

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: Gigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPU: Intel Core™ i5-14400F
Cores: 16 total (16 perf)
Frequency: 2.5 GHz
RAM: 32 GB DDR4
GPU: NVIDIA GeForce RTX 5060 Ti
OS: Microsoft Windows 11 Professionnel 10.0.26200
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 27.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.4
First chunk latency Delay before the first streamed chunk arrives from runtime: 86 ms
Time to first token How fast the model starts responding — lower is better: 86 ms
Load time Time to load the model into memory before inference: 7.2 s
Memory usage RAM consumed during inference — percentage of total system memory: 12.6 GB (40%)
Total tokens Total number of tokens generated across all benchmark prompts: 1128

Score breakdown

Speed

43/50

Time to first token

20/20

Memory

28/30

Quality

Reasoning

11/20

Coding

17/20

Instruction following

11/20

Structured output

13/15

Math

7/15

Multilingual

10/10

Category levels

Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.34.0
Model format: GGUF
Hardware profile: BALANCED
Result hash: b14cb622a6e523a8ce8b8215ee9e20b89f2eaf8e1f67bc58248f35fabdd14b01

Interpretation

Hardware fit: 91/100. Overall suitability: GOOD (Global 76/100). Category profile: Reasoning: Adequate, Coding: Strong, Instruction Following: Adequate, Structured Output: Strong, Math: Weak, Multilingual: Strong.

Bench Environment

CPU load: avg 20% (peak 22%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest