whatmodel.sh / Meditron 7B

Meditron 7B

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

Meditron 7B is an open-weights language model from EPFL LLM, released November 2023. Its published size is 6.74B parameters. Licence: llama2.

Catalogue identity notes

Maker repo epfl-llm/meditron-7b @d7d0a5e: licence tag llama2. 6,738,554,880 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2023-11: month the maker's Hugging Face repo was created (createdAt 2023-11-08). Pretrained base checkpoint (not an instruct/chat version). Gated repository (licence acceptance required on Hugging Face).

18.3±5.7#922 of 949 LLMsfrom 2 benchmark results across 2 sources* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Meditron 7B, out of 1132 with a score, then more from EPFL LLM.

#modelscorewhereRAMreleased
1100OPT-2.7B Meta19±1local~7.1GB2022-05
1101SmolLM2 360M Instruct Hugging Face19±3local~1.7GB2024-10
1102Meditron 7B EPFL LLM18±6local~5.5GB2023-11
1103GPT-Neo 2.7B EleutherAI18±1local~13GB2021-03
1104GPT-3 babbage (API base model) OpenAI18±1comparison only2020-06
more from EPFL LLM
908Meditron 70B EPFL LLM38±4local~32GB2023-11

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests2 not in a task · 86% of its score
testresultvs the others in its rundifficultycountswhy
BRIDGE clinical text, zero-shot average (87 tasks)9.5% ✎▃▁▁▁▁▂▂▃▄▆█▃ beats 0/97hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 66%blunt
SurgiQ surgical MCQ (zero-shot, log-probability scoring)27.1% ✎▃···▂▂·▃▂▃██ beats 0/17medium · avg 53%▇▇▇▇▇▇▇▇ 19%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 Meditron 7B · needs ~4.1 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/meditron-7B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/meditron-7B-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 Meditron 7B · needs ~4.1 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/meditron-7B-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 Meditron 7B · needs ~4.1 GB · from huggingface.co/TheBloke
    chat in the terminal
    ollama run hf.co/TheBloke/meditron-7B-GGUF: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 Meditron 7B · needs ~3.8 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/meditron-7b
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/meditron-7b

Other ways to run it

  1. Run it as published · needs ~13.48 GB · from huggingface.co/epfl-llm (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='epfl-llm/meditron-7b', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/epfl-llm ↗

$ how the score was worked out · BRIDGE Medical Leaderboard (H… 66%, SurgiQ: A Large-Scale Multi-D… 19%

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
BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 66%MIT
SurgiQ: A Large-Scale Multi-Domain Benchmark for Evaluating Surgical Understanding in Large Language Models (arXiv:2606.08071v1)1▇▇▇▇▇▇ 19%CC BY 4.0
prior · pull toward the middle▇▇▇▇ 14%
weighted average= 18.3

$ 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