8-bit Open on Hugging Face
Parameters
451M
Weights (est.)
≈ 560 MB
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/LFM2-VL-450M-8bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- —
- Vendor
- —
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- lfm1.0
- Downloads
- 285 in the last 30 days · 5.1K all time · 11 likes
- Published
- 2025-08-16 · updated 2025-08-16 (1y ago)
- Languages
- en
- Tags
- lfm2-vl, liquid, lfm2, edge, custom_code