Picsart-AI-Research · First MLX build 24 Jun 2026
MI-GAN
MLX
Image mit
A 7M parameter image to image model from Picsart-AI-Research, with 3 MLX builds at fp16.
- Parameters
- 7M From Hugging Face
- Quantisation
- fp16 MI-GAN-256-ffhq-fp16
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 13 MB Weights, estimated
- Downloads
- 0 This build, last 30 days
- Task
- Image to image Image
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at fp16
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/MI-GAN-256-ffhq-fp16MLX builds
3 on mlx-community| MI-GAN-256-ffhq-fp16 | fp16 | 13 MB | 3 GB | 0 |
|---|---|---|---|---|
| MI-GAN-256-places2-fp16 | fp16 | 13 MB | 3 GB | 0 |
| MI-GAN-512-places2-fp16 | fp16 | 15 MB | 3 GB | 0 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.