4-bit Open on Hugging Face
Parameters
4.2B
Weights (est.)
≈ 2.4 GB
Mac memory (est.)
8 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/Fara1.5-4B-OptiQ-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- microsoft/Fara1.5-4B (quantized)
- Vendor
- Microsoft · Phi
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 130 in the last 30 days · 761 all time · 2 likes
- Published
- 2026-07-24 · updated 2026-10-18 (24d ago)
- Languages
- en
- Tags
- qwen3_5, optiq, computer-use, web-agent, agent
Other MLX builds of microsoft/Fara1.5-4B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Fara1.5-4B-OptiQ-4bit (this one) | 4-bit | ≈ 2.4 GB | 8 GB+ | 130 |
| Fara1.5-4B-8bit | 8-bit | ≈ 5.1 GB | 8 GB+ | 50 |