inclusionAI · First MLX build 28 May 2026
LLaDA2.1-mini
MLX
TextVision apache-2.0
A 16B parameter vision and text model from inclusionAI, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 16B From Hugging Face
- Quantisation
- 4-bit LLaDA2.1-mini-4bit
- Memory needed
- 13 GB Estimate, unified memory
- Download
- 9.2 GB Weights, estimated
- Downloads
- 47 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 13 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/LLaDA2.1-mini-4bit --image photo.jpg --prompt "Describe this image"MLX builds
3 on mlx-community| LLaDA2.1-mini-4bit | 4-bit | 9.2 GB | 13 GB | 47 |
|---|---|---|---|---|
| LLaDA2.1-mini-5bit | 5-bit | 11.2 GB | 15 GB | 29 |
| LLaDA2.1-mini-bf16 | bf16 | 32.5 GB | 39 GB | 22 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.