What are the hardware requirements for Gemma 3n E2B 4bit?

Gemma 3n E2B 4bit requires approximately 4.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma 3n E2B 4bit and how large is it?

Gemma 3n E2B 4bit is developed by mlx-community, a model with 1.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Gemma 3n E2B 4bit perform on standard benchmarks?

Gemma 3n E2B 4bit has the following published scores: LMSYS ELO 1318. Compare against reference models on this page or on the LLM Explorer leaderboards.

Gemma 3n E2B 4bit by mlx-community — VRAM 4.5GB

Name: Gemma 3n E2B 4bit
Author: mlx-community

Gemma 3n E2B 4bit is an open-source language model by mlx-community. Features: 1.7b LLM, VRAM: 4.5GB, License: gemma, Quantized, LLM Explorer Score: 0.32, ELO: 1318.

4-bit 4bit Audio-text-to-text Automatic-speech-recognition Automatic-speech-translation Base model:google/gemma-3n-e4b Base model:quantized:google/ge... Endpoints compatible Gemma3n Image-text-to-text Mlx Quantized Region:us Safetensors Video-text-to-text

Model Card on HF 🤗: https://huggingface.co/mlx-community/gemma-3n-E2B-4bit

Gemma 3n E2B 4bit Benchmarks

LMSys ELO 1318 vs 1272 (so35) 3.6%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Gemma 3n E2B 4bit Parameters and Internals

LLM Name	Gemma 3n E2B 4bit
Repository 🤗	https://huggingface.co/mlx-community/gemma-3n-E2B-4bit
Base Model(s)	Gemma 3n E4B google/gemma-3n-E4B
Model Size	1.7b
Required VRAM	4.5 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	gemma3n
Model Files	4.5 GB
Quantization Type	4bit
Model Architecture	Gemma3nForConditionalGeneration
License	gemma
Transformers Version	4.53.2
Padding Token	<pad>

Rank the Gemma 3n E2B 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

Best Alternatives to Gemma 3n E2B 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 3n E2B It 4bit	0K / 4.5 GB	481	10