MLX Community · First MLX build 16 Aug 2025
LFM2-VL-450M
MLX
TextVision lfm1.0
A 451M parameter vision and text model, with 5 MLX builds, from 4-bit to 6-bit.
- Parameters
- 451M From Hugging Face
- Quantisation
- 4-bit LFM2-VL-450M-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 377 MB Weights, estimated
- Downloads
- 4.5K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at 4-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-VL-450M-4bit --image photo.jpg --prompt "Describe this image"MLX builds
5 on mlx-community| LFM2-VL-450M-4bit | 4-bit | 377 MB | 3 GB | 4.5K |
|---|---|---|---|---|
| LFM2-VL-450M-5bit | 5-bit | 423 MB | 3 GB | 37 |
| LFM2-VL-450M-8bit | 8-bit | 560 MB | 3 GB | 290 |
| LFM2-VL-450M-bf16 | bf16 | 902 MB | 4 GB | 28 |
| LFM2-VL-450M-6bit | 6-bit | — | — | 0 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.