gemma-4-12B-coder-fable5-composer2.5-v1-OptiQ-4bit
mlx-community/gemma-4-12B-coder-fable5-composer2.5-v1-OptiQ-4bit
Vision + text · mlx
4-bit Open on Hugging Face
Parameters
12B
Weights (est.)
≈ 6.8 GB
Mac memory (est.)
16 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/gemma-4-12B-coder-fable5-composer2.5-v1-OptiQ-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1 (quantized)
- Vendor
- yuxinlu1
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 1.0K in the last 30 days · 7.5K all time · 11 likes
- Published
- 2026-07-14 · updated 2026-10-18 (24d ago)
- Tags
- gemma4_unified, quantized, mixed-precision, 4bit, 8bit, optiq, apple-silicon, vision-language, gemma4, coding, code, reasoning
Other MLX builds of yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated-4bit-msq | 4-bit | ≈ 1.8 GB | 8 GB+ | 107 |
| gemma-4-12b-coder-fable5-composer2.5-4bit | 4-bit | ≈ 6.7 GB | 16 GB+ | 6.7K |
| gemma-4-12B-coder-fable5-composer2.5-v1-OptiQ-4bit (this one) | 4-bit | ≈ 6.8 GB | 16 GB+ | 1.0K |
| gemma-4-12b-coder-fable5-composer2.5-8bit | 8-bit | ≈ 12.7 GB | 24 GB+ | 968 |
| gemma-4-12b-coder-fable5-composer2.5 | — | ≈ 23.8 GB | 32 GB+ | 149 |