HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

medgemma-27b-it

google/medgemma-27b-it

kind
original
quant
bf16 (16-bit)
family
gemma
modality
image-text-to-text
root model
google/gemma-3-27b-pt
provider
google
license
other
language
—
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
118,825
likes
395
created
—
last modified
2025-07-10T01:37:38+00:00 (2025)
huggingface
https://huggingface.co/google/medgemma-27b-it
tags
transformerssafetensorsgemma3image-text-to-textmedicalx-raypathologydermatologyfundusradiology report generationchest-x-raymedical-embeddingsimage-classificationzero-shot-image-classificationimage-feature-extractionconversationalenarxiv:2303.15343arxiv:2507.05201arxiv:2405.03162arxiv:2106.14463arxiv:2412.03555arxiv:2501.19393arxiv:2009.13081

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
MMLUknowledge67.2MMLU Medmedium| MMLU Med | 67.2 | 70.0 | 83.3 | 87.0 | 86.2 |
MedQAdomain50.7MedQA (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) |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.