What are the hardware requirements for Medgemma 4B It Unsloth Bnb 4bit?

Medgemma 4B It Unsloth Bnb 4bit requires approximately 4.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Medgemma 4B It Unsloth Bnb 4bit and how large is it?

Medgemma 4B It Unsloth Bnb 4bit is developed by unsloth, a model with 4b 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 4B It Unsloth Bnb 4bit?

Medgemma 4B It Unsloth Bnb 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Medgemma 4B It Unsloth Bnb 4bit by unsloth — VRAM 4.1GB

Name: Medgemma 4B It Unsloth Bnb 4bit
Author: unsloth

Medgemma 4B It Unsloth Bnb 4bit is an open-source language model by unsloth. Features: 4b LLM, VRAM: 4.1GB, License: other, Quantized, LLM Explorer Score: 0.19.

Arxiv:2009.13081 Arxiv:2102.09542 Arxiv:2106.14463 Arxiv:2303.15343 Arxiv:2405.03162 Arxiv:2411.15640 Arxiv:2412.03555 Arxiv:2501.18362 Arxiv:2501.19393 4-bit 4bit Base model:google/medgemma-4b-... Base model:quantized:google/me... Bitsandbytes Chest-x-ray Clinical-reasoning Conversational Dermatology Endpoints compatible Gemma3 Image-text-to-text Medical Ophthalmology Pathology Quantized Radiology Region:us Safetensors Unsloth

Model Card on HF 🤗: https://huggingface.co/unsloth/medgemma-4b-it-unsloth-bnb-4bit

Medgemma 4B It Unsloth Bnb 4bit Parameters and Internals

LLM Name	Medgemma 4B It Unsloth Bnb 4bit
Repository 🤗	https://huggingface.co/unsloth/medgemma-4b-it-unsloth-bnb-4bit
Base Model(s)	google/medgemma-4b-it google/medgemma-4b-it
Model Size	4b
Required VRAM	4.1 GB
Updated	2026-08-10
Maintainer	unsloth
Model Type	gemma3
Model Files	4.1 GB
Quantization Type	4bit
Model Architecture	Gemma3ForConditionalGeneration
License	other
Model Max Length	131072
Transformers Version	4.51.3
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Torch Data Type	bfloat16

Rank the Medgemma 4B It Unsloth Bnb 4bit 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

Quantized Models of the Medgemma 4B It Unsloth Bnb 4bit

Model	Likes	Downloads	VRAM
Medgemma 4B Radiology Reports	15	188	8 GB

Best Alternatives to Medgemma 4B It Unsloth Bnb 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 3 4B It Unsloth Bnb 4bit	0K / 4.6 GB	23457	26
Gemma 3 4B It Bnb 4bit	0K / 3.2 GB	13443	12
...a 3 4B It Qat Q4 0 Unquantized	0K / 8.6 GB	1016	11
Gemma 3 4B It Qat	0K / 8.6 GB	58	1
Selene Rebel 4B Instruct	0K / 8.6 GB	79	1
...4B It 4bit Immersive Translate	0K / 2.2 GB	1338	10
...4B It 4bit Immersive Translate	0K / 2.2 GB	28	1
Translategemma 4B It 4bit	0K / 2.2 GB	1619	9
Medgemma 1.5 4B It Bnb 4bit	0K / 3.8 GB	448	6
Translategemma 4B It 8bit	0K / 4.1 GB	440	5

Note: green Score (e.g. "73.2") means that the model is better than unsloth/medgemma-4b-it-unsloth-bnb-4bit.