MLX Community · First MLX build 2 Sept 2026
moge-3-vitl
MLX
Vision mit
A 370M parameter depth estimation model, with one MLX build at fp32.
- Parameters
- 370M From Hugging Face
- Quantisation
- fp32 moge-3-vitl-mlx-fp32
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.5 GB Weights, estimated
- Downloads
- 140 This build, last 30 days
- Task
- Depth estimation Vision
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at fp32
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/moge-3-vitl-mlx-fp32MLX builds
1 on mlx-community| moge-3-vitl-mlx-fp32 | fp32 | 1.5 GB | 4 GB | 140 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.