whatmodel.sh / Devstral Small 2 24B

Devstral Small 2 24B

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

Devstral Small 2 24B is an open-weights language model from Mistral, released December 2025. Its published size is 24B parameters and a 262k-token context window. Licence: apache-2.0.

60.9±2.7#186 of 719 LLMsfrom 3 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Devstral Small 2 24B, out of 828 with a score, then more from Mistral.

#modelscorewhereRAMreleased
220Llama 3.1 Nemotron Ultra 253B v1 NVIDIA61±2local~82GB2025-04
221HyperCLOVA X SEED 32B Think NAVER Cloud61±2comparison only2025-12
222Devstral Small 2 24B Mistral61±3local~17GB2025-12
223o1-mini OpenAI61±1comparison only2024-09
224Gemini 2.0 Pro Experimental (02-05) Google61±1comparison only2025-02
more from Mistral
79Mistral Large 4 (public preview) Mistral71±2api $2.06/M2026-10
174Mistral Medium 3.5 (128B) Mistral65±1api $3.00/M +local~42GB2026-04
180Mistral Medium 3.1 (2508) Mistral64±2comparison only2025-08

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks█··········█ #2 of 2 · 97% of its score · 3 tests
testresultvs the others in its rundifficultycountswhy
SWE-bench Verified lab68.0% ✎▁▁▁▁▁▁▂▄█▆▁▁ beats 69/131hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 40%sharp · at its level · small run
Terminal-Bench 2.0 lab22.5% ✎▂▂▅▅████▆▂▃▃ beats 3/36very hard · avg 11%▇▇▇▇▇▇▇▇▇▇▇▇▇ 32%at its level · small run
SWE-bench Multilingual lab55.7% ✎▁··▁▃▂▅▇█▃▃▁ beats 16/60hard · avg 30%▇▇▇▇▇▇▇▇▇▇ 25%at its level · small run
coding▁▁▁▃▆██▇▆▄▃▁ #129 of 458 * · 65% of its score · 2 tests

Beats Qwen3.5 Plus, Gemini 2.5 Pro, Gemini 3.1 Flash-Lite here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
SWE-bench Verified lab68.0% ✎▁▁▁▁▁▁▂▄█▆▁▁ beats 69/131hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 40%sharp · at its level · small run
SWE-bench Multilingual lab55.7% ✎▁··▁▃▂▅▇█▃▃▁ beats 16/60hard · avg 30%▇▇▇▇▇▇▇▇▇▇ 25%at its level · small run

$ 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 Devstral Small 2 24B · needs ~14.3 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/Devstral-Small-2-24B-Instruct-2512-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf lmstudio-community/Devstral-Small-2-24B-Instruct-2512-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 Devstral Small 2 24B · needs ~14.3 GB · from huggingface.co/lmstudio-community

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/lmstudio-community/Devstral-Small-2-24B-Instruct-2512-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 Devstral Small 2 24B · needs ~14.9 GB · from ollama.com
    chat in the terminal
    ollama run devstral-small-2:24b

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Devstral Small 2 24B · needs ~15.1 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit

Weights and documentation: huggingface.co/mistralai ↗

$ how the score was worked out · mistralai/Devstral-Small-2-24… 97%

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
mistralai/Devstral-Small-2-24B-Instruct-2512 model card · lab-reported3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 97%Apache-2.0
prior · pull toward the middle▇ 3%
weighted average= 60.9

$ 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