LLM EXPLORER 67,552 MODELS INDEXED

Gemma 4 E4B It Qat Bf16 by mlx-community

By mlx-community · 77 downloads

Gemma 4 E4B It Qat Bf16 is an open-source language model by mlx-community. Features: 7.9b LLM, VRAM: 15.9GB, LLM Explorer Score: 0.23.

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

Gemma 4 E4B It Qat Bf16 Parameters and Internals

LLM NameGemma 4 E4B It Qat Bf16
Repository πŸ€—https://huggingface.co/mlx-community/gemma-4-E4B-it-qat-bf16 
Model Size7.9b
Required VRAM15.9 GB
Updated2026-08-08
Maintainermlx-community
Model Typegemma4
Model Files  5.4 GB: 1-of-4   3.9 GB: 2-of-4   5.6 GB: 3-of-4   1.0 GB: 4-of-4
Supported Languagesen
Model ArchitectureGemma4ForConditionalGeneration
Transformers Version5.6.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 E4B It Qat Bf16

Best Alternatives
Context / RAM
Downloads
Likes
Basal Omni 2.0 Mini Preview0K / 15.9 GB942
Basal Omni 1.0 Mini0K / 15.9 GB10943
Nirnaya Flash 1.00K / 0.2 GB661
Gemma 4 E4B It Heretic0K / 15.9 GB840
...tron 3.5 Bolt E4B BF16 Heretic0K / 15.9 GB1091
Kitsune Tales E4B EN0K / 15.9 GB2981
Kitsune Tales E4B JP0K / 15.9 GB2891
Baihua Gemma4 E4B0K / 15.9 GB1353
Firehouse Cactus 1.00K / 15.9 GB7360
ContextPilot E4B0K / 15.9 GB4045
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gemma-4-E4B-it-qat-bf16.