MLX Community · First MLX build 11 Jan 2026
Molmo2-8B
MLX
TextVision apache-2.0
A 8.7B parameter video and text model, with 5 MLX builds, from 4-bit to fp16.
- Parameters
- 8.7B From Hugging Face
- Quantisation
- 4-bit Molmo2-8B-4bit
- Memory needed
- 10 GB Estimate, unified memory
- Download
- 6.4 GB Weights, estimated
- Downloads
- 205 This build, last 30 days
- Task
- Video and text Text, Vision
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 10 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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Molmo2-8B-4bitMLX builds
5 on mlx-community| Molmo2-8B-4bit | 4-bit | 6.4 GB | 10 GB | 205 |
|---|---|---|---|---|
| Molmo2-8B-5bit | 5-bit | 7.4 GB | 11 GB | 42 |
| Molmo2-8B-6bit | 6-bit | 8.3 GB | 12 GB | 47 |
| Molmo2-8B-8bit | 8-bit | 10.2 GB | 14 GB | 92 |
| Molmo2-8B-fp16 | fp16 | 17.3 GB | 22 GB | 41 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.