whatmodel.sh / MMed-Llama-3-8B

MMed-Llama-3-8B

+ contribute

MMed-Llama-3-8B is an open-weights language model from SJTU MedLLM (Henrychur), released May 2024. Its published size is 8.03B parameters. Licence: llama3.

Catalogue identity notes

Maker repo Henrychur/MMed-Llama-3-8B @6c3057b: licence tag llama3. 8,030,261,248 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-05: month the maker's Hugging Face repo was created (createdAt 2024-05-22). Pretrained base checkpoint (not an instruct/chat version).

37.1±5.1#770 of 949 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of MMed-Llama-3-8B, out of 1132 with a score.

#	model	score	where	RAM	released
933	DeepSeek R1 Distill Qwen 1.5B DeepSeek	37±2	local	~2.6GB	2025-01
934	Gemma 2 2B IT Google	37±1	local	~3.1GB	2024-07
935	MMed-Llama-3-8B SJTU MedLLM (Henrychur)	37±5	local	~6.6GB	2024-05
936	Qwen2.5 Coder 0.5B Instruct Alibaba	37±1	local	~1.8GB	2024-11
937	Granite 20B Code Base (8K) IBM	37±1	local	~15GB	2024-04

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 89% of its score

test	result	vs the others in its run	difficulty	counts	why
BRIDGE clinical text, zero-shot average (87 tasks)	20.4% ✎	▁▁▁▁▁▃▂▃▄▆█▃ beats 10/97	hard · avg 32%	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 89%	blunt

$ where to run it

llama.cpp · recommended

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 ↗
Run MMed-Llama-3-8B · needs ~4.9 GB · from huggingface.co/Axcel1
chat in the terminal
llama cli -hf Axcel1/MMed-Llama-3-8B-Q4_K_M-GGUF:q4_k_m
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf Axcel1/MMed-Llama-3-8B-Q4_K_M-GGUF:q4_k_m

LM Studio

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run MMed-Llama-3-8B · needs ~4.9 GB · from huggingface.co/Axcel1
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/Axcel1/MMed-Llama-3-8B-Q4_K_M-GGUF@q4_k_m -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run MMed-Llama-3-8B · needs ~4.9 GB · from huggingface.co/Axcel1
chat in the terminal
ollama run hf.co/Axcel1/MMed-Llama-3-8B-Q4_K_M-GGUF:q4_k_m

Other ways to run it

Run it as published · needs ~32.12 GB · from huggingface.co/Henrychur
uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='Henrychur/MMed-Llama-3-8B', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Weights and documentation: huggingface.co/Henrychur ↗

$ how the score was worked out · BRIDGE Medical Leaderboard (H… 89%

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

source	results	share of the score	licence
BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)	1	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 89%	MIT
prior · pull toward the middle		▇▇▇ 11%
weighted average		= 37.1

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit 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 2026-10-11 02:20 UTC · sources and licences · json