whatmodel.sh / Mathstral 7B v0.1

Mathstral 7B v0.1

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

Mathstral 7B v0.1 is an open-weights language model from Mistral AI, released July 2024. Its published size is 7.25B parameters and a 32k-token context window. Licence: apache-2.0.

Catalogue identity notes

Maker repo mistralai/Mathstral-7B-v0.1 @ec3a484: licence tag apache-2.0. 7,248,023,552 parameters from the Hugging Face safetensors metadata. Dense, so active = total. Released 2024-07: month the maker's Hugging Face repo was created (createdAt 2024-07-16). Ollama tags mathstral:7b-v0.1-q4_K_M, mathstral:7b-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.

42.3±1.4#497 of 719 LLMsfrom 4 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Mathstral 7B v0.1, out of 828 with a score, then more from Mistral AI.

#modelscorewhereRAMreleased
585Aya Vision 32B Cohere42±3api price unknown +local~71GB2025-03
586Tulu 2 DPO 70B Ai242±1local~32GB2023-11
587Mathstral 7B v0.1 Mistral AI42±1local~5.8GB2024-07
588Yi-1.5 9B (base) 01.AI42±2local~6.8GB2024-05
589Claude Instant 1.2 Anthropic42±1comparison only2023-08
more from Mistral AI
419Codestral 22B v0.1 Mistral AI50±1local~15GB2024-05
425Mistral Small Instruct 22B (2409) Mistral AI49±2local~15GB2024-09
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

math▁▂▃▅▆▅▄█▄▁▁▁ #304 of 398 * · 4.8% of its score · 1 test

Beats GPT-4 (0613), Athene-70B, Llama 3 70B Instruct here, though they rank higher overall. Trails Gemma 7B (base), DeepSeek R1 Distill Qwen 1.5B, CodeGemma 7B (v1.0) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
MATH (subset unspecified) lab56.6% ✎▂▄▄▃█▇▅▆▄▃▄▁ beats 33/80easy · avg 66%▇▇ 4.8%at its level · noisy
other tests3 not in a task · 94% of its score
testresultvs the others in its rundifficultycountswhy
LiveBench 2024-07-2624.5% ✎▁▁▁▂▂▃▃█▆▃▅▃ beats 18/61medium · avg 41%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 57%at its level
MMLU-Pro42.0% ✎▃▂▅█▃·█▃▅··▂ beats 9/23medium · avg 57%▇▇▇▇▇▇▇▇▇▇▇ 26%at its level
ZebraLogic (ZeroEval, 1,000 puzzles)9.0% ✎▁▁▃▆██▁▁·▁▁▁ beats 7/57hard · avg 18%▇▇▇▇ 11%sharp · too hard for it

$ 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 Mathstral 7B v0.1 · needs ~4.4 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/mathstral-7B-v0.1-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf lmstudio-community/mathstral-7B-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 Mathstral 7B v0.1 · needs ~4.4 GB · from huggingface.co/lmstudio-community

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/lmstudio-community/mathstral-7B-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 Mathstral 7B v0.1 · needs ~4.85 GB · from ollama.com
    chat in the terminal
    ollama run mathstral:7b-v0.1-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 Mathstral 7B v0.1 · needs ~4.1 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/mathstral-7B-v0.1-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/mathstral-7B-v0.1-4bit

Official weights and documentation: huggingface.co/mistralai ↗

$ how the score was worked out · LiveBench model judgments (HF… 57%, MMLU-Pro author-released eval… 26%, WildEval ZeroEval published r… 11% 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
LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 57%Apache-2.0 (stated in the LiveBench datasheet)
MMLU-Pro author-released evaluation runs1▇▇▇▇▇▇▇▇ 26%Apache-2.0
WildEval ZeroEval published results1▇▇▇ 11%Apache-2.0
Mistral AI vendor-reported benchmark scores for its own models (Hugging Face model cards) · lab-reported1▇ 5%Factual vendor-reported score (not licensed content)
prior · pull toward the middle▇ 1%
weighted average= 42.3

$ 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