MLX Community · First MLX build 21 Mar 2026
MolmoPoint-8B
MLX
TextVision apache-2.0
A 8.7B parameter vision and text model, with 8 MLX builds, from 4-bit to fp16.
- Parameters
- 8.7B From Hugging Face
- Quantisation
- 4-bit MolmoPoint-8B-4bit
- Memory needed
- 11 GB Estimate, unified memory
- Download
- 7.2 GB Weights, estimated
- Downloads
- 110 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 8 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 11 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/MolmoPoint-8B-4bit --image photo.jpg --prompt "Describe this image"MLX builds
8 on mlx-community| MolmoPoint-8B-4bit | 4-bit | 7.2 GB | 11 GB | 110 |
|---|---|---|---|---|
| MolmoPoint-8B-nvfp4 | 4-bit | 7.2 GB | 11 GB | 51 |
| MolmoPoint-8B-mxfp4 | MXFP4 | 7.2 GB | 11 GB | 35 |
| MolmoPoint-8B-5bit | 5-bit | 8.1 GB | 12 GB | 46 |
| MolmoPoint-8B-6bit | 6-bit | 9.0 GB | 13 GB | 53 |
| MolmoPoint-8B-8bit | 8-bit | 10.7 GB | 15 GB | 56 |
| MolmoPoint-8B-mxfp8 | MXFP8 | 10.7 GB | 15 GB | 33 |
| MolmoPoint-8B-fp16 | fp16 | 17.4 GB | 22 GB | 33 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.