whatmodel.sh / Magistral Small 1.0 (2506)

Magistral Small 1.0 (2506)

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

Magistral Small 1.0 (2506) is an open-weights language model from Mistral, released June 2025. Its published size is 23.57B parameters and a 128k-token context window. Licence: apache-2.0.

Catalogue identity notes

Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2025-06-10). Magistral Small 1.0 (version 25.06; API id retired 11/30/2025); distinct from magistral-small-2509 (1.2). 23,572,403,200 parameters.

55.2±1.2#260 of 719 LLMsfrom 8 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Magistral Small 1.0 (2506), out of 828 with a score, then more from Mistral.

#modelscorewhereRAMreleased
310Mistral Large 2 (2411) Mistral55±1local~78GB2024-11
311Ministral 3 8B Reasoning 2512 Mistral55±1local~6.5GB2025-12
312Magistral Small 1.0 (2506) Mistral55±1local~16GB2025-06
313Qwen3 30B-A3B (Apr 2025, hybrid) Alibaba55±1api $0.35/M +local~19GB2025-04
314Molmo 2 8B Ai255±2local~6.8GB2025-12
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▁▁▃▆█▆▅▅▅▄▃▁ #276 of 300 * · 2.3% of its score · 1 test

Trails Granite 4.0 H 350M, Qwen3 0.6B, Qwen2.5 1.5B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Galileo Agent Leaderboard v2 (action completion)16.0% ✎▅▃·▃▃▅▅█▃█▅▅ beats 1/19hard · avg 27%▇ 2.3%at its level
coding██········██ #4 of 4 * · 6.7% of its score · 1 test

Trails Magistral Small 1.1 (2507) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LiveCodeBench v5 (window unspecified) lab55.8% ✎▄█▄······▄·▄ beats 0/5medium · avg 50%▇▇▇ 6.7%at its level
math▁▂▃▅▆▅▄█▄▁▁▁ #198 of 398 · 45% of its score · 3 tests

Beats MiniMax-M2.1, Qwen3 235B-A22B (Apr 2025, hybrid), DeepSeek V3 (Dec '24) here, though they rank higher overall. Trails Phi-4-mini-reasoning 3.8B, DeepSeek R1 Distill Qwen 7B, OpenThinker2 7B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AIME 2025 lab62.8% ✎█▃·····▃···▃ beats 2/5medium · avg 49%▇▇▇▇▇▇▇▇ 20%sharp · at its level
AIME 2024 lab70.7% ✎█▃·····▃···▃ beats 1/5medium · avg 60%▇▇▇▇▇▇▇ 16%sharp · at its level
OTIS mock AIME 2024–202530.0% ✎▃▃▄▃▃▃▇▇█▃▂▅ beats 64/193very hard · avg 8.5%▇▇▇ 8.7%sharp · noisy
other tests2 not in a task · 46% of its score
testresultvs the others in its rundifficultycountswhy
GPQA Diamond +156.1% ✎▁▁▁▁▂▄▆▄▅▇█▅ beats 80/208hard · avg 40%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 39%sharp · at its level · several runs
BRIDGE clinical text, zero-shot average (87 tasks)37.6% ✎▁▁▁▁▁▂▂▃▄▆█▃ beats 58/97hard · avg 32%▇▇▇ 6.5%blunt · at its level

$ 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 Magistral Small 1.0 (2506) · needs ~14.3 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/mistralai_Magistral-Small-2506-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/mistralai_Magistral-Small-2506-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 Magistral Small 1.0 (2506) · needs ~14.3 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-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 Magistral Small 1.0 (2506) · needs ~14.64 GB · from ollama.com
    chat in the terminal
    ollama run magistral:24b-small-2506-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 Magistral Small 1.0 (2506) · needs ~13.3 GB, Mac only · from huggingface.co/lmstudio-community
    chat in the terminal
    mlx_lm.chat --model lmstudio-community/Magistral-Small-2506-MLX-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model lmstudio-community/Magistral-Small-2506-MLX-4bit

Weights and documentation: huggingface.co/mistralai ↗

$ how the score was worked out · mistralai/Magistral-Small-250… 62%, Epoch AI — internal evaluatio… 29%, BRIDGE Medical Leaderboard (H… 7% 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
mistralai/Magistral-Small-2509 model card · lab-reported4▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 62%Apache-2.0
Epoch AI — internal evaluations2▇▇▇▇▇▇▇▇▇ 29%CC BY 4.0
BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)1▇▇ 7%MIT
Galileo Agent Leaderboard (v1 and v2 results)1▇ 2%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 55.2

$ 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