yuxinlu1 · First MLX build 21 Jun 2026
gemma-4-12B-coder-fable5-composer2.5-v1
MLX
TextVision apache-2.0
A 12B parameter vision and text model from yuxinlu1, with 2 MLX builds at 4-bit.
- Parameters
- 12B From Hugging Face
- Quantisation
- 4-bit gemma-4-12B-coder-fable5-composer2.5-v1-OptiQ-4bit
- Memory needed
- 10 GB Estimate, unified memory
- Download
- 6.8 GB Weights, estimated
- Downloads
- 1.0K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 10 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 · mlx-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/gemma-4-12B-coder-fable5-composer2.5-v1-OptiQ-4bit --image photo.jpg --prompt "Describe this image"MLX builds
2 on mlx-community| Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated-4bit-msq | 4-bit | 1.8 GB | 4 GB | 105 |
|---|---|---|---|---|
| gemma-4-12B-coder-fable5-composer2.5-v1-OptiQ-4bit | 4-bit | 6.8 GB | 10 GB | 1.0K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.