medgemma-27b-it

Home/Models/unsloth/medgemma-27b-it

unsloth/medgemma-27b-it

kind: original
quant: bf16 (16-bit)
family: gemma
modality: image-text-to-text
root model: google/medgemma-27b-it
provider: unsloth
license: other
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 368
likes: 3
created: —
last modified: 2025-07-10T05:24:32+00:00 (2025)
huggingface: https://huggingface.co/unsloth/medgemma-27b-it
tags: transformerssafetensorsgemma3image-text-to-textmedicalunsloth - x-ray - pathology - dermatology - fundus - radiology report generation - chest-x-ray - medical-embeddings - image-classification - zero-shot-image-classification - image-feature-extraction - image-text-to-textconversationalenarxiv:2303.15343arxiv:2507.05201arxiv:2405.03162arxiv:2106.14463arxiv:2412.03555arxiv:2501.19393arxiv:2009.13081arxiv:2102.09542arxiv:2411.15640arxiv:2404.05590arxiv:2501.18362base_model:google/medgemma-27b-itbase_model:finetune:google/medgemma-27b-itlicense:othertext-generation-inferenceendpoints_compatible

benchmark	category	score	context	conf	evidence
MMLU	knowledge	67.2	MMLU Med	medium	`\| MMLU Med \| 67.2 \| 70.0 \| 83.3 \| 87.0 \| 86.2 \|`
MedQA	domain	50.7	MedQA (4-op)	medium	`\| MedQA (4-op) \| 50.7 \| 64.4 \| 74.9 \| 89.8 (best-of-5) 87.7 (0-shot) \| 87.0 (best-of-5) 85.3 (0-shot) \|`

none scraped.