MLX Community · First MLX build 19 Jun 2026
gemma-4-12b-coder-fable5-composer2.5
MLX
Text apache-2.0
A 12B parameter text generation model, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 12B From Hugging Face
- Quantisation
- 4-bit gemma-4-12b-coder-fable5-composer2.5-4bit
- Memory needed
- 10 GB Estimate, unified memory
- Download
- 6.7 GB Weights, estimated
- Downloads
- 6.6K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 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-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/gemma-4-12b-coder-fable5-composer2.5-4bit --prompt "Hello"MLX builds
3 on mlx-community| gemma-4-12b-coder-fable5-composer2.5-4bit | 4-bit | 6.7 GB | 10 GB | 6.6K |
|---|---|---|---|---|
| gemma-4-12b-coder-fable5-composer2.5-8bit | 8-bit | 12.7 GB | 17 GB | 999 |
| gemma-4-12b-coder-fable5-composer2.5 | Unstated | 23.8 GB | 29 GB | 149 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.