whatmodel.sh / AntAngelMed

AntAngelMed

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

AntAngelMed is an open-weights language model from MedAIBase (Ant Group), released December 2025. Its published size is 102.89B parameters (6.1B active per token). Licence: apache-2.0.

Catalogue identity notes

Maker repo MedAIBase/AntAngelMed @5325cdd: licence tag apache-2.0. 102,889,705,216 parameters from the Hugging Face safetensors metadata; active 6.1B per token (AntAngelMed card: 'activating only 6.1B parameters of its 100B parameters'). Released 2025-12: month the maker's Hugging Face repo was created (createdAt 2025-12-12).

54.6±4.4#328 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 AntAngelMed, out of 1132 with a score.

#modelscorewhereRAMreleased
429Olmo 3.1 32B Instruct Ai255±2local~21GB2025-12
430ToolACE-8B Team-ACE (Huawei Noah's Ark & USTC)55±6local~6.6GB2024-08
431AntAngelMed MedAIBase (Ant Group)55±4local~41GB2025-12
432HuatuoGPT-o1-70B FreedomIntelligence (CUHK-SZ)55±4local~22GB2024-12
433OpenThinker 32B Open Thoughts55±1local~21GB2025-02

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 91% of its score
testresultvs the others in its rundifficultycountswhy
BRIDGE clinical text, zero-shot average (87 tasks)36.6% ✎▁▁▁▁▁▂▂▃▄▆█▃ beats 52/97hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 91%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 AntAngelMed · needs ~62.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/AntAngelMed-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/AntAngelMed-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 AntAngelMed · needs ~62.4 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/AntAngelMed-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run AntAngelMed · needs ~37.7 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/AntAngelMed-GGUF:Q2_K

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 AntAngelMed · needs ~57.9 GB, Mac only · from huggingface.co/laukerry
    chat in the terminal
    mlx_lm.chat --model laukerry/AntAngelMed-mlx-4Bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model laukerry/AntAngelMed-mlx-4Bit

Other ways to run it

  1. Run it as published · needs ~205.78 GB · from huggingface.co/MedAIBase (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='MedAIBase/AntAngelMed', torch_dtype='auto', device_map='auto', trust_remote_code=True)('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/MedAIBase ↗

$ how the score was worked out · BRIDGE Medical Leaderboard (H… 91%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 91%MIT
prior · pull toward the middle▇▇▇ 9%
weighted average= 54.6

$ 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