MLX Community · First MLX build 22 Oct 2025
LFM2-VL-3B
MLX
TextVision lfm1.0
A 3B parameter vision and text model, with 5 MLX builds, from 4-bit to bf16.
- Parameters
- 3B From Hugging Face
- Quantisation
- 4-bit LFM2-VL-3B-4bit
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 2.3 GB Weights, estimated
- Downloads
- 215 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 5 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-3B-4bit --image photo.jpg --prompt "Describe this image"MLX builds
5 on mlx-community| LFM2-VL-3B-4bit | 4-bit | 2.3 GB | 5 GB | 215 |
|---|---|---|---|---|
| LFM2-VL-3B-5bit | 5-bit | 2.6 GB | 5 GB | 46 |
| LFM2-VL-3B-6bit | 6-bit | 2.9 GB | 6 GB | 33 |
| LFM2-VL-3B-8bit | 8-bit | 3.6 GB | 6 GB | 40 |
| LFM2-VL-3B-bf16 | bf16 | 6.0 GB | 9 GB | 30 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.