Google · First MLX build 2 Apr 2026
gemma-4-e4b
MLX
TextVisionAudio apache-2.0
A 8B parameter any to any model from Google, with 6 MLX builds, from 4-bit to bf16.
- Parameters
- 8B From Hugging Face
- Quantisation
- 4-bit gemma-4-e4b-4bit
- Memory needed
- 8 GB Estimate, unified memory
- Download
- 5.2 GB Weights, estimated
- Downloads
- 447 This build, last 30 days
- Task
- Any to any Text, Vision, Audio
- MLX builds
- 6 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 8 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/gemma-4-e4b-4bitMLX builds
6 on mlx-community| gemma-4-e4b-4bit | 4-bit | 5.2 GB | 8 GB | 447 |
|---|---|---|---|---|
| gemma-4-e4b-5bit | 5-bit | 6.2 GB | 9 GB | 58 |
| gemma-4-e4b-6bit | 6-bit | 7.1 GB | 10 GB | 60 |
| gemma-4-e4b-8bit | 8-bit | 9.0 GB | 13 GB | 209 |
| gemma-4-e4b-mxfp8 | MXFP8 | 9.0 GB | 13 GB | 46 |
| gemma-4-e4b-bf16 | bf16 | 16.0 GB | 20 GB | 46 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.