What are the hardware requirements for Medgemma 4B It Text Only?

Medgemma 4B It Text Only requires approximately 7.8 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Medgemma 4B It Text Only and how large is it?

Medgemma 4B It Text Only is developed by electricsheepafrica, 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 Text Only?

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

Medgemma 4B It Text Only by electricsheepafrica — VRAM 7.8GB, 8K context

Name: Medgemma 4B It Text Only
Author: electricsheepafrica

Medgemma 4B It Text Only is an open-source language model by electricsheepafrica. Features: 4b LLM, VRAM: 7.8GB, Context: 8K, License: apache-2.0, LLM Explorer Score: 0.21.

Africa Base model:finetune:google/med... Base model:google/medgemma-4b-... Chw Conversational Endpoints compatible Gemma Gemma3 text Healthcare Medical Region:us Safetensors Vllm

Model Card on HF 🤗: https://huggingface.co/electricsheepafrica/medgemma-4b-it-text-only

Medgemma 4B It Text Only Parameters and Internals

LLM Name	Medgemma 4B It Text Only
Repository 🤗	https://huggingface.co/electricsheepafrica/medgemma-4b-it-text-only
Base Model(s)	google/medgemma-4b-it google/medgemma-4b-it
Model Size	4b
Required VRAM	7.8 GB
Updated	2026-10-19
Maintainer	electricsheepafrica
Model Type	gemma3_text
Model Files	7.8 GB
Model Architecture	Gemma3ForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.49.0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	262208
Torch Data Type	bfloat16

Rank the Medgemma 4B It Text Only 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 4B It Text Only

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 3 4B T1 It	128K / 9.1 GB	27	41
KONI 4B Instruct 20250901	128K / 7.8 GB	206	2
Nile Chat 4B	128K / 7.8 GB	760	19
Gemma 3 4B Cpt It 0820	128K / 7.8 GB	16	0
Gemma 3 4B Cpt It 0821	128K / 7.8 GB	5	0
Typhoon2.1 Gemma3 4B	128K / 7.8 GB	744	10
EEVE Rosetta 4B 2507	128K / 7.8 GB	14	8
Gemma 3 4B It Abliterated V2	128K / 15.5 GB	200	11
Typhoon2.1 Gemma3 4B	128K / 7.8 GB	232	6
Gemma 3 4B Tigrinya	128K / 7.8 GB	20	1

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