numind · First MLX build 20 May 2026
NuExtract3
MLX
TextVision
A 4.5B parameter vision and text model from numind, with one MLX build at bf16.
- Parameters
- 4.5B From Hugging Face
- Quantisation
- bf16 NuExtract3-bf16
- Memory needed
- 13 GB Estimate, unified memory
- Download
- 9.1 GB Weights, estimated
- Downloads
- 62 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 13 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/NuExtract3-bf16 --image photo.jpg --prompt "Describe this image"MLX builds
1 on mlx-community| NuExtract3-bf16 | bf16 | 9.1 GB | 13 GB | 62 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.