whatmodel.sh / Llama3-OpenBioLLM-8B

Llama3-OpenBioLLM-8B

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

Llama3-OpenBioLLM-8B is an open-weights language model from Saama AI Labs, released April 2024. Licence: llama3.

Catalogue identity notes

Maker repo aaditya/Llama3-OpenBioLLM-8B @70d6bb5: licence tag llama3. Released 2024-04: month the maker's Hugging Face repo was created (createdAt 2024-04-20).

40.2±2.1#528 of 719 LLMsfrom 4 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Llama3-OpenBioLLM-8B, out of 828 with a score.

#modelscorewhereRAMreleased
618OpenHermes-2.5-Code-290k-13B ajibawa-202341±1local~9.8GB2024-03
619Granite 4.0 H 1B IBM40±1local~2.3GB2025-10
620Llama3-OpenBioLLM-8B Saama AI Labs40±2local~6.6GB2024-04
621Nous Hermes 2 Mistral 7B DPO Nous Research40±2local~6.1GB2024-02
622Nous Hermes 2 Mixtral 8x7B DPO Nous Research40±2local~31GB2024-01

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests4 not in a task · 98% of its score
testresultvs the others in its rundifficultycountswhy
MedQA (USMLE, 4 options)57.8% ✎▁▁··▄▁▁··▄▃█ beats 15/17easy · avg 76%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 51%sharp · at its level
MedMCQA57.8% ✎▂▂··▄▄▂▂·▄██ beats 17/17medium · avg 68%▇▇▇▇▇▇▇▇▇▇▇ 27%at its level
BRIDGE clinical text, zero-shot average (87 tasks)14.2% ✎▁▁▃▁▁▂▂▃▄▆█▃ beats 2/97hard · avg 32%▇▇▇▇▇▇▇ 17%blunt
PubMedQA72.0% ✎▂·▂▆·▄▂▄▄▃█▂ beats 12/17medium · avg 77%▇ 2.9%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 Llama3-OpenBioLLM-8B · needs ~4.9 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/Llama3-OpenBioLLM-8B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/Llama3-OpenBioLLM-8B-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 Llama3-OpenBioLLM-8B · needs ~4.9 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/Llama3-OpenBioLLM-8B-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 Llama3-OpenBioLLM-8B · needs ~4.9 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/Llama3-OpenBioLLM-8B-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 Llama3-OpenBioLLM-8B · needs ~5.3 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Llama3-OpenBioLLM-8B
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Llama3-OpenBioLLM-8B

Other ways to run it

  1. Run it as published · needs ~16.06 GB · from huggingface.co/aaditya
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='aaditya/Llama3-OpenBioLLM-8B', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Weights and documentation: huggingface.co/aaditya ↗

$ how the score was worked out · Open Medical-LLM Leaderboard… 81%, BRIDGE Medical Leaderboard (H… 17%

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
Open Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%Apache-2.0
BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)1▇▇▇▇▇ 17%MIT
prior · pull toward the middle▇ 2%
weighted average= 40.2

$ 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