LLM EXPLORER 59,516 MODELS INDEXED

Gemma 4 E4B It Qat 4bit by mlx-community

By mlx-community · 1408 downloads

Gemma 4 E4B It Qat 4bit is an open-source language model by mlx-community. Features: 2.1b LLM, VRAM: 6.7GB, Quantized, LLM Explorer Score: 0.28.

  4-bit   4bit   Conversational   En   Gemma4   Image-text-to-text   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Gemma 4 E4B It Qat 4bit Parameters and Internals

LLM NameGemma 4 E4B It Qat 4bit
Repository πŸ€—https://huggingface.co/mlx-community/gemma-4-E4B-it-qat-4bit 
Model Size2.1b
Required VRAM6.7 GB
Updated2026-08-08
Maintainermlx-community
Model Typegemma4
Model Files  4.2 GB: 1-of-2   2.5 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureGemma4ForConditionalGeneration
Transformers Version5.6.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 E4B It Qat 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 E4b It 6bit0K / 7.1 GB10963
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gemma-4-E4B-it-qat-4bit.