LLM EXPLORER 57,252 MODELS INDEXED

Gemma 3n E4B It Lm Bf16 by mlx-community

By mlx-community · 88 downloads
HF Repo ↗ Copy URL

Gemma 3n E4B It Lm Bf16 is an open-source language model by mlx-community. Features: 6.9b LLM, VRAM: 13.8GB, License: gemma, LLM Explorer Score: 0.32, ELO: 1318.

  Audio-text-to-text   Automatic-speech-recognition   Automatic-speech-translation Base model:finetune:google/gem... Base model:google/gemma-3n-e4b...   Conversational   Gemma3n   Mlx   Region:us   Safetensors   Sharded   Tensorflow   Video-text-to-text
Model Card on HF 🤗: https://huggingface.co/mlx-community/gemma-3n-E4B-it-lm-bf16 

Gemma 3n E4B It Lm Bf16 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").

Gemma 3n E4B It Lm Bf16 Parameters and Internals

LLM NameGemma 3n E4B It Lm Bf16
Repository 🤗https://huggingface.co/mlx-community/gemma-3n-E4B-it-lm-bf16 
Base Model(s)  Gemma 3n E4B It   google/gemma-3n-E4B-it
Model Size6.9b
Required VRAM13.8 GB
Updated2026-07-27
Maintainermlx-community
Model Typegemma3n
Model Files  5.4 GB: 1-of-3   3.6 GB: 2-of-3   4.8 GB: 3-of-3
Model ArchitectureGemma3nForConditionalGeneration
Licensegemma
Transformers Version4.53.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Torch Data Typebfloat16