Liquid AI · First MLX build 22 Apr 2026
LFM2.5-VL-450M
MLX
TextVision lfm1.0
A 449M parameter vision and text model from Liquid AI, with 2 MLX builds, from 6-bit to 8-bit.
- Parameters
- 449M From Hugging Face
- Quantisation
- 6-bit LFM2.5-VL-450M-6bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 467 MB Weights, estimated
- Downloads
- 1.4K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at 6-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/LFM2.5-VL-450M-6bit --image photo.jpg --prompt "Describe this image"MLX builds
2 on mlx-community| LFM2.5-VL-450M-6bit | 6-bit | 467 MB | 3 GB | 1.4K |
|---|---|---|---|---|
| LFM2.5-VL-450M-8bit | 8-bit | 557 MB | 3 GB | 60 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.