4-bit Open on Hugging Face
Parameters
3.0B
Weights (est.)
≈ 2.3 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/LFM2-VL-3B-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- —
- Vendor
- —
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- lfm1.0
- Downloads
- 205 in the last 30 days · 4.3K all time · 4 likes
- Published
- 2025-10-22 · updated 2026-01-15 (10mo ago)
- Languages
- en, ja, fr, es, de, it, pt, ar, zh, ko
- Tags
- lfm2_vl, liquid, lfm2, lfm2-vl, edge