whatmodel.sh / Magistral Small 1.1 (2507)

Magistral Small 1.1 (2507)

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

Magistral Small 1.1 (2507) is an open-weights language model from Mistral, released July 2025. Its published size is 23.57B parameters and a 40k-token context window. Licence: apache-2.0.

Catalogue identity notes

Mistral docs: 'Magistral Small 1.1 ... July 24, 2025 Retired Apache 2.0 v 25.07 ... magistral-small-2507 ... Retirement date 11/30/2025' (API retired; weights remain). Weights mistralai/Magistral-Small-2507 @b3583a4 (created 2025-07-18, apache-2.0). Distinct from catalogued magistral-small-2506 (1.0) and magistral-small-2509 (1.2).

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 23,572,403,200 (BF16).

54.5±1.5#274 of 719 LLMsfrom 4 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Magistral Small 1.1 (2507), out of 828 with a score, then more from Mistral.

#modelscorewhereRAMreleased
326Olmo 3.1 32B Instruct Ai255±2local~21GB2025-12
327OpenThinker 32B Open Thoughts55±1local~21GB2025-02
328Magistral Small 1.1 (2507) Mistral55±2local~16GB2025-07
329EXAONE Deep 7.8B LG AI Research55±2local~6.5GB2025-03
330Qwen2.5-Math 72B Instruct Alibaba55±2local~44GB2024-09
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

coding██········██ #3 of 4 * · 11% of its score · 1 test

Beats Magistral Small 1.0 (2506) here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
LiveCodeBench v5 (window unspecified) lab59.2% ✎▄█▄······▄·▄ beats 1/5medium · avg 50%▇▇▇▇ 11%at its level
math▁▂▃▅▆▅▄█▄▁▁▁ #205 of 398 * · 59% of its score · 2 tests

Beats DeepSeek V3 (Dec '24), GPT-4o (2024-08-06), Command A (03-2025) here, though they rank higher overall. Trails Olmo 3 7B Instruct, DeepSeek R1 Distill Llama 8B, Phi-4-mini-reasoning 3.8B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AIME 2025 lab62.0% ✎█▃·····▃···▃ beats 1/5medium · avg 49%▇▇▇▇▇▇▇▇▇▇▇▇▇ 32%sharp · at its level
AIME 2024 lab70.5% ✎█▃·····▃···▃ beats 0/5medium · avg 60%▇▇▇▇▇▇▇▇▇▇▇ 27%sharp · at its level
other tests1 not in a task · 30% of its score
testresultvs the others in its rundifficultycountswhy
GPQA Diamond lab65.8% ✎█·█·███····█ beats 0/5medium · avg 53%▇▇▇▇▇▇▇▇▇▇▇▇ 30%sharp · 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 1.1 (2507) · needs ~14.3 GB · from huggingface.co/mistralai
    chat in the terminal
    llama cli -hf mistralai/Magistral-Small-2507-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mistralai/Magistral-Small-2507-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 1.1 (2507) · needs ~14.3 GB · from huggingface.co/mistralai

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mistralai/Magistral-Small-2507-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 1.1 (2507) · needs ~14.3 GB · from huggingface.co/mistralai
    chat in the terminal
    ollama run hf.co/mistralai/Magistral-Small-2507-GGUF:Q4_K_M

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 Magistral Small 1.1 (2507) · needs ~13.3 GB, Mac only · from huggingface.co/lmstudio-community
    chat in the terminal
    mlx_lm.chat --model lmstudio-community/Magistral-Small-2507-MLX-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model lmstudio-community/Magistral-Small-2507-MLX-4bit

Other ways to run it

  1. Run it as published · needs ~47.14 GB, NVIDIA only · from huggingface.co/mistralai
    vllm serve mistralai/Magistral-Small-2507 --reasoning-parser mistral --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2

Weights and documentation: huggingface.co/mistralai ↗

$ how the score was worked out · mistralai/Magistral-Small-250… 99%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 54.5

$ 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