LLM EXPLORER 61,652 MODELS INDEXED

Gemma 4 E4b It OptiQ 4bit by mlx-community

By mlx-community · 4587 downloads
HF Repo ↗ Copy URL

Gemma 4 E4b It OptiQ 4bit is an open-source language model by mlx-community. Features: 7.5b LLM, VRAM: 6.5GB, Context: 128K, License: gemma, Quantized, LLM Explorer Score: 0.28.

  4-bit   4bit   8bit   Apple-silicon   Conversational   Gemma-4   Gemma4   Mixed-precision   Mlx   Optiq   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/gemma-4-e4b-it-OptiQ-4bit 

Gemma 4 E4b It OptiQ 4bit Parameters and Internals

LLM NameGemma 4 E4b It OptiQ 4bit
Repository 🤗https://huggingface.co/mlx-community/gemma-4-e4b-it-OptiQ-4bit 
Base Model(s)  google/gemma-4-e4b-it   google/gemma-4-e4b-it
Model Size7.5b
Required VRAM6.5 GB
Updated2026-07-26
Maintainermlx-community
Model Typegemma4
Model Files  3.5 GB: 1-of-2   3.0 GB: 2-of-2
Quantization Type4bit
Model ArchitectureGemma4ForConditionalGeneration
Licensegemma
Context Length131072
Model Max Length131072
Transformers Version5.5.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size262144

Quantized Models of the Gemma 4 E4b It OptiQ 4bit

Model
Likes
Downloads
VRAM
...litan Translator V0 Gemma4 E4b23126 GB
...litan Translator V0 Gemma4 E4b2766 GB

Best Alternatives to Gemma 4 E4b It OptiQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 E4b It Qat OptiQ 4bit0K / 6.5 GB28036
... 4 E4B It OBLITERATED Mlx 8Bit0K / 8 GB24814
...litan Translator V0 Gemma4 E4b0K / 6.5 GB3122
...litan Translator V0 Gemma4 E4b0K / 6.5 GB762
Supergemma4 E4b Abliterated0K / 15.1 GB66079
MedusaGemma E4B0K / 15.1 GB191
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gemma-4-e4b-it-OptiQ-4bit.