whatmodel.sh / Codestral 22B v0.1

Codestral 22B v0.1

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Codestral 22B v0.1 is an open-weights language model from Mistral AI, released May 2024. Its published size is 22.25B parameters and a 32k-token context window. Licence: mnpl.

Catalogue identity notes

Maker repo mistralai/Codestral-22B-v0.1 @28b1c1a: licence tag other (mnpl). 22,247,282,688 parameters from the Hugging Face safetensors metadata. Dense, so active = total. Released 2024-05: month the maker's Hugging Face repo was created (createdAt 2024-05-29). Ollama tags codestral:22b-v0.1-q4_K_M, codestral:22b-v0.1-q8_0 are the library's instruct/chat builds of this checkpoint (tag names on the pinned tags page); download sizes are estimated from the parameter count.

49.7±0.8#349 of 719 LLMsfrom 7 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Codestral 22B v0.1, out of 828 with a score, then more from Mistral AI.

#modelscorewhereRAMreleased
417Qwen2.5-VL 7B Instruct Alibaba50±1local~6.4GB2025-01
418Molmo 72B (0924) Ai250±2local~309GB2024-09
419Codestral 22B v0.1 Mistral AI50±1local~15GB2024-05
420GLM-4 (0116) Z.ai50±1comparison only2024-01
421Llama 3 70B Instruct Meta50±0local~24GB2024-04
more from Mistral AI
425Mistral Small Instruct 22B (2409) Mistral AI49±2local~15GB2024-09
587Mathstral 7B v0.1 Mistral AI42±1local~5.8GB2024-07
612Mixtral 8x7B v0.1 (base) Mistral AI41±1local~29GB2023-12

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #260 of 458 · 91% of its score · 4 tests

Beats Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B), GLM-4.7-Flash here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, QwQ-32B-Preview, Phi-3 Medium 128K Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval79.9% ✎▁·▁▁▃▄▆▅█▃▁▁ beats 84/99easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 40%sharp
HumanEval+73.8% ✎▁·▁▁▁▃▄▄▄█▃▁ beats 84/99easy · avg 74%▇▇▇▇▇▇▇▇▇▇▇▇▇ 34%sharp · at its level
Aider code editing (133 Exercism Python exercises, two attempts)51.1% ✎▁·▁▂▄▁▆▄█▆▂▂ beats 17/62medium · avg 54%▇▇▇▇▇ 12%at its level
MBPP+61.9% ✎▁···▁▁▂▅▇█▆▂ beats 41/75easy · avg 68%▇▇▇ 6.7%at its level
other tests3 not in a task · 8.3% of its score
testresultvs the others in its rundifficultycountswhy
EvalPerf correctness (118 tasks, 20240328)72.8% ✎▂·▂▂▂▆▅▆▆▆▃█ beats 8/29easy · avg 76%▇▇ 3.8%typical
DSEffi-Bench Pass (1,000 data-science tasks, greedy)27.4% ✎▅··▃▅·█·▃██▃ beats 2/15hard · avg 24%▇ 3.2%typical
Open PT-LLM Leaderboard average (9 Portuguese tasks)71.0% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 179/276medium · avg 73%▇ 1.3%at its level · noisy

$ where to run it

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run Codestral 22B v0.1 · needs ~13.3 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/Codestral-22B-v0.1-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/Codestral-22B-v0.1-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Codestral 22B v0.1 · needs ~13.3 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Codestral 22B v0.1 · needs ~13.85 GB · from ollama.com
    chat in the terminal
    ollama run codestral:22b-v0.1-q4_K_M

MLX (Mac)

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Codestral 22B v0.1 · needs ~12.5 GB, Mac only · from huggingface.co/rairahulr1
    chat in the terminal
    mlx_lm.chat --model rairahulr1/Codestral-22B-v0.1-mlx-4Bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model rairahulr1/Codestral-22B-v0.1-mlx-4Bit

Official weights and documentation: huggingface.co/mistralai ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 84%, Aider code editing benchmark… 12%, DSEffi-Bench: Demystifying La… 3% and 1 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
EvalPlus / EvalPerf published evaluation runs4▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 84%Apache-2.0
Aider code editing benchmark runs (old edit leaderboard)1▇▇▇ 12%Apache-2.0
DSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation — authors' own model runs1▇ 3%CC BY 4.0
Open Portuguese LLM Leaderboard (archived)1▇ 1%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 49.7

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json