What are the hardware requirements for Gemma 3n E4B?

Gemma 3n E4B requires approximately 15.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma 3n E4B and how large is it?

Gemma 3n E4B is developed by unsloth, a model with 8.4b 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 Gemma 3n E4B?

Gemma 3n E4B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gemma 3n E4B by unsloth — VRAM 15.8GB

Name: Gemma 3n E4B
Author: unsloth

Gemma 3n E4B is an open-source language model by unsloth. Features: 8.4b LLM, VRAM: 15.8GB, License: gemma, LLM Explorer Score: 0.19.

Base model:finetune:google/gem... Base model:google/gemma-3n-e4b En Endpoints compatible Gemma Gemma3 Gemma3n Google Image-text-to-text Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/unsloth/gemma-3n-E4B

Gemma 3n E4B Parameters and Internals

LLM Name	Gemma 3n E4B
Repository 🤗	https://huggingface.co/unsloth/gemma-3n-E4B
Base Model(s)	google/gemma-3n-E4B google/gemma-3n-E4B
Model Size	8.4b
Required VRAM	15.8 GB
Updated	2026-08-10
Maintainer	unsloth
Model Type	gemma3n
Model Files	3.1 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 2.7 GB: 4-of-4
Supported Languages	en
Model Architecture	Gemma3nForConditionalGeneration
License	gemma
Model Max Length	32768
Transformers Version	4.53.1
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Torch Data Type	bfloat16

Rank the Gemma 3n E4B 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 Gemma 3n E4B

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 3n E4B It	0K / 15.8 GB	8181	10
Gemma 3n E4B It Bf16	0K / 15.8 GB	137	12
Gemma 3n E4B Bf16	0K / 15.8 GB	57	7

Note: green Score (e.g. "73.2") means that the model is better than unsloth/gemma-3n-E4B.