8-bit Open on Hugging Face
Parameters
9.4B
Weights (est.)
≈ 10.4 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/Fara1.5-9B-8bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- microsoft/Fara1.5-9B (quantized)
- Vendor
- Microsoft · Phi
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- mit
- Downloads
- 59 in the last 30 days · 417 all time · 2 likes
- Published
- 2026-07-29 · updated 2026-07-29 (3mo ago)
- Languages
- en
- Tags
- qwen3_5, computer-use, web-agent, multimodal, vision-language, agent, browser-automation, magentic, fara
Other MLX builds of microsoft/Fara1.5-9B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Fara1.5-9B-OptiQ-4bit | 4-bit | ≈ 6.0 GB | 16 GB+ | 160 |
| Fara1.5-9B-8bit (this one) | 8-bit | ≈ 10.4 GB | 16 GB+ | 59 |