datalab-to · First MLX build 27 Jun 2026
lift
MLX
TextVision openrail
A 9.4B parameter vision and text model from datalab-to, with 7 MLX builds, from 3-bit to bf16.
- Parameters
- 9.4B From Hugging Face
- Quantisation
- 4-bit lift-oQ4
- Memory needed
- 9 GB Estimate, unified memory
- Download
- 6.0 GB Weights, estimated
- Downloads
- 37 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 7 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 9 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/lift-oQ4 --image photo.jpg --prompt "Describe this image"MLX builds
7 on mlx-community| lift-oQ3.5 | 3-bit | 4.8 GB | 8 GB | 19 |
|---|---|---|---|---|
| lift-oQ3 | 3-bit | 4.8 GB | 8 GB | 18 |
| lift-oQ4 | 4-bit | 6.0 GB | 9 GB | 37 |
| lift-oQ5 | 5-bit | 7.1 GB | 10 GB | 23 |
| lift-oQ6 | 6-bit | 8.2 GB | 12 GB | 20 |
| lift-oQ8 | 8-bit | 10.4 GB | 14 GB | 29 |
| lift-bf16 | bf16 | 18.8 GB | 24 GB | 21 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.