whatmodel.sh / Hulu-Med-32B

Hulu-Med-32B

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

Hulu-Med-32B is an open-weights language model from ZJU AI4H, released October 2025. Its published size is 33.21B parameters. Licence: apache-2.0.

Catalogue identity notes

Maker repo ZJU-AI4H/Hulu-Med-32B @dfac09d: licence tag apache-2.0. 33,208,146,672 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2025-10: month the maker's Hugging Face repo was created (createdAt 2025-10-09). Comparison-only here: no run command was verified for this checkpoint (multimodal model with custom HulumedQwen modelling code; see the model card for its own inference script).

56.1±4.4comparison only: no current run option verifiedfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Hulu-Med-32B, out of 1132 with a score, then more from ZJU AI4H.

#modelscorewhereRAMreleased
379Grok 2 (1212) SpaceXAI (xAI)56±1comparison only2024-12
380Qwen3-VL 4B Thinking Alibaba56±1local~4.1GB2025-10
381Hulu-Med-32B ZJU AI4H56±4comparison only2025-10
382EXAONE Deep 32B LG AI Research56±2local~22GB2025-03
383DeepSeek R1 Distill Qwen 32B DeepSeek56±1api $1.59/M +local~21GB2025-01
more from ZJU AI4H
469Hulu-Med-14B ZJU AI4H53±4comparison only2025-10
616Hulu-Med-7B ZJU AI4H49±5comparison only2025-10

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)38.3% ✎▁▁▁▁▁▂▂▃▄▆█▃ beats 62/97hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 91%blunt · at its level

$ where to run it

No verified API or download recorded yet · add one

Official weights and documentation: huggingface.co/ZJU-AI4H ↗

$ 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= 56.1

$ 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