MLX Community · First MLX build 3 Mar 2025
UI-TARS-72B-SFT
MLX
TextVision apache-2.0
A 73B parameter vision and text model, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 73B From Hugging Face
- Quantisation
- bf16 UI-TARS-72B-SFT-bf16
- Memory needed
- 167 GB Estimate, unified memory
- Download
- 147 GB Weights, estimated
- Downloads
- 35 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 167 GB at bf16
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/UI-TARS-72B-SFT-bf16 --image photo.jpg --prompt "Describe this image"MLX builds
4 on mlx-community| UI-TARS-72B-SFT-4bit | 4-bit | 42.3 GB | 50 GB | 28 |
|---|---|---|---|---|
| UI-TARS-72B-SFT-6bit | 6-bit | 60.5 GB | 70 GB | 23 |
| UI-TARS-72B-SFT-8bit | 8-bit | 78.7 GB | 90 GB | 26 |
| UI-TARS-72B-SFT-bf16 | bf16 | 147 GB | 167 GB | 35 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.