HF Model & Benchmark Matrix
Overview
Benchmarks
Speech
Models
Orgs
24,078 variants · 14,984 scores · 120 benchmarks
Home
/
Models
/
google/medgemma-4b-it
medgemma-4b-it
google/medgemma-4b-it
kind
original
quant
bf16 (16-bit)
family
gemma
modality
image-text-to-text
root model
google/medgemma-4b-pt
provider
google
license
other
language
—
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
294,639
likes
1,025
created
—
last modified
2025-10-28T17:24:49+00:00
(2025)
huggingface
https://huggingface.co/google/medgemma-4b-it
tags
transformers
safetensors
gemma3
image-text-to-text
medical
radiology
clinical-reasoning
dermatology
pathology
ophthalmology
chest-x-ray
conversational
arxiv:2303.15343
arxiv:2507.05201
arxiv:2405.03162
arxiv:2106.14463
arxiv:2412.03555
arxiv:2501.19393
arxiv:2009.13081
arxiv:2102.09542
arxiv:2411.15640
arxiv:2404.05590
arxiv:2501.18362
base_model:google/medgemma-4b-pt
Benchmark scores (2)
benchmark
category
score
context
conf
evidence
MMLU
knowledge
67.2
MMLU Med
medium
| MMLU Med | 67.2 | 70.0 |
MedQA
domain
50.7
MedQA (4-op)
medium
| MedQA (4-op) | 50.7 | 64.4 |
Discussions (0)
none scraped.
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.