MLX Community · First MLX build 12 Mar 2025
gemma-3-4b-it
MLX
TextVision gemma
A 5B parameter vision and text model, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 5B From Hugging Face
- Quantisation
- 8-bit gemma-3-4b-it-8bit
- Memory needed
- 9 GB Estimate, unified memory
- Download
- 5.7 GB Weights, estimated
- Downloads
- 17K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 9 GB at 8-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 · mlx-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/gemma-3-4b-it-8bit --image photo.jpg --prompt "Describe this image"MLX builds
4 on mlx-community| gemma-3-4b-it-4bit | 4-bit | 3.4 GB | 6 GB | 2.7K |
|---|---|---|---|---|
| gemma-3-4b-it-6bit | 6-bit | 4.5 GB | 8 GB | 47 |
| gemma-3-4b-it-8bit | 8-bit | 5.7 GB | 9 GB | 17K |
| gemma-3-4b-it-bf16 | bf16 | 9.9 GB | 14 GB | 657 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.