inclusionAI · First MLX build 20 Mar 2026
UI-Venus-1.5-8B
MLX
TextVision apache-2.0
A 8.8B parameter vision and text model from inclusionAI, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 8.8B From Hugging Face
- Quantisation
- 4-bit UI-Venus-1.5-8B-4bit
- Memory needed
- 9 GB Estimate, unified memory
- Download
- 5.8 GB Weights, estimated
- Downloads
- 44 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 3 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/UI-Venus-1.5-8B-4bit --image photo.jpg --prompt "Describe this image"MLX builds
3 on mlx-community| UI-Venus-1.5-8B-4bit | 4-bit | 5.8 GB | 9 GB | 44 |
|---|---|---|---|---|
| UI-Venus-1.5-8B-6bit | 6-bit | 7.8 GB | 11 GB | 35 |
| UI-Venus-1.5-8B-bf16 | bf16 | 17.5 GB | 22 GB | 25 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.