8-bit Open on Hugging Face
Parameters
449M
Weights (est.)
≈ 557 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/LFM2.5-VL-450M-8bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- LiquidAI/LFM2.5-VL-450M (quantized)
- Vendor
- LiquidAI
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- lfm1.0
- Downloads
- 58 in the last 30 days · 733 all time · 0 likes
- Published
- 2026-04-22 · updated 2026-08-13 (3mo ago)
- Languages
- en, ja, ko, fr, es, de, ar, zh, pt
- Tags
- lfm2_vl, liquid, lfm2, lfm2-vl, edge, lfm2.5-vl, lfm2.5, mlx-vlm, 8bit, quantized
Other MLX builds of LiquidAI/LFM2.5-VL-450M
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| LFM2.5-VL-450M-6bit | 6-bit | ≈ 467 MB | 8 GB+ | 1.4K |
| LFM2.5-VL-450M-8bit (this one) | 8-bit | ≈ 557 MB | 8 GB+ | 58 |