What are the hardware requirements for Medgemma 27B It?

Medgemma 27B It requires approximately 55.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Medgemma 27B It and how large is it?

Medgemma 27B It is developed by unsloth, a model with 27b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Medgemma 27B It?

Medgemma 27B It is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Medgemma 27B It by unsloth — VRAM 55.3GB

Name: Medgemma 27B It
Author: unsloth

Medgemma 27B It is an open-source language model by unsloth. Features: 27b LLM, VRAM: 55.3GB, License: other, LLM Explorer Score: 0.2.

Arxiv:2009.13081 Arxiv:2102.09542 Arxiv:2106.14463 Arxiv:2303.15343 Arxiv:2404.05590 Arxiv:2405.03162 Arxiv:2411.15640 Arxiv:2412.03555 Arxiv:2501.18362 Arxiv:2501.19393 Arxiv:2507.05201 Base model:finetune:google/med... Base model:google/medgemma-27b... Conversational En Endpoints compatible Gemma3 Image-text-to-text Medical Region:us Safetensors Sharded Tensorflow Unsloth - x-ray - pathology - ...

Model Card on HF 🤗: https://huggingface.co/unsloth/medgemma-27b-it

Medgemma 27B It Parameters and Internals

LLM Name	Medgemma 27B It
Repository 🤗	https://huggingface.co/unsloth/medgemma-27b-it
Base Model(s)	google/medgemma-27b-it google/medgemma-27b-it
Model Size	27b
Required VRAM	55.3 GB
Updated	2026-08-10
Maintainer	unsloth
Model Type	gemma3
Model Files	4.8 GB: 1-of-12 5.0 GB: 2-of-12 5.0 GB: 3-of-12 5.0 GB: 4-of-12 5.0 GB: 5-of-12 5.0 GB: 6-of-12 5.0 GB: 7-of-12 5.0 GB: 8-of-12 5.0 GB: 9-of-12 5.0 GB: 10-of-12 5.0 GB: 11-of-12 0.5 GB: 12-of-12
Supported Languages	en
Model Architecture	Gemma3ForConditionalGeneration
License	other
Model Max Length	131072
Transformers Version	4.53.1
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Torch Data Type	bfloat16

Rank the Medgemma 27B It capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Medgemma 27B It

Best Alternatives	Context / RAM	Downloads	Likes
Fallen Gemma3 27B V1	128K / 55.3 GB	90	49
Gemma 3 27B It	0K / 55.3 GB	769066	2006
Translategemma 27B It	0K / 55.3 GB	16445	390
MamayLM Gemma 3 27B IT V2.0	0K / 55.2 GB	1875	8
Gemma 3 27B It Quantized.w4a16	0K / 19.8 GB	329829	13
Gemma 3 27B It	0K / 55.3 GB	42790	16
Translategemma 27B It Bf16	0K / 54 GB	65	1
Gemma 3 27B It Abliterated	0K / 55.3 GB	2762	336
Gemma SEA LION V4 27B IT	0K / 55.2 GB	1221	24
Gemma 3 27B Pt	0K / 55.3 GB	8304	124

Note: green Score (e.g. "73.2") means that the model is better than unsloth/medgemma-27b-it.