Ai2 · First MLX build 20 Oct 2026
Molmo2-8B
MLX
TextVision apache-2.0
A 8.7B parameter vision and text model from Ai2, with one MLX build at MXFP4.
- Parameters
- 8.7B From Hugging Face
- Quantisation
- MXFP4 Molmo2-8B-mxfp4
- Memory needed
- 10 GB Estimate, unified memory
- Download
- 6.4 GB Weights, estimated
- Downloads
- 211 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 10 GB at MXFP4
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/Molmo2-8B-mxfp4 --image photo.jpg --prompt "Describe this image"MLX builds
1 on mlx-community| Molmo2-8B-mxfp4 | MXFP4 | 6.4 GB | 10 GB | 211 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.