LLM EXPLORER 55,709 MODELS INDEXED

Gemma 3n E2B Bf16 by mlx-community

By mlx-community · 21 downloads
HF Repo ↗ Copy URL

Gemma 3n E2B Bf16 is an open-source language model by mlx-community. Features: 6b LLM, VRAM: 10.8GB, License: gemma.

  Audio-text-to-text   Automatic-speech-recognition   Automatic-speech-translation Base model:finetune:google/gem...   Base model:google/gemma-3n-e4b   Endpoints compatible   Gemma3n   Image-text-to-text   Mlx   Region:us   Safetensors   Sharded   Tensorflow   Video-text-to-text
Model Card on HF 🤗: https://huggingface.co/mlx-community/gemma-3n-E2B-bf16 

Gemma 3n E2B Bf16 Parameters and Internals

LLM NameGemma 3n E2B Bf16
Repository 🤗https://huggingface.co/mlx-community/gemma-3n-E2B-bf16 
Base Model(s)  google/gemma-3n-E4B   google/gemma-3n-E4B
Model Size6b
Required VRAM10.8 GB
Updated2026-08-08
Maintainermlx-community
Model Typegemma3n
Model Files  4.8 GB: 1-of-3   5.3 GB: 2-of-3   0.7 GB: 3-of-3
Model ArchitectureGemma3nForConditionalGeneration
Licensegemma
Transformers Version4.53.2
Padding Token<pad>