Fediory · First MLX build 27 Jul 2026
HVI-CIDNet
MLX
Image mit
A 2M parameter image to image model from Fediory, with 3 MLX builds at fp32.
- Parameters
- 2M From Hugging Face
- Quantisation
- fp32 HVI-CIDNet-Generalization-fp32
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 8 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 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/HVI-CIDNet-Generalization-fp32MLX builds
3 on mlx-community| HVI-CIDNet-Generalization-fp32 | fp32 | 8 MB | 3 GB | 0 |
|---|---|---|---|---|
| HVI-CIDNet-LOLv1-fp32 | fp32 | 8 MB | 3 GB | 0 |
| HVI-CIDNet-SICE-fp32 | fp32 | 8 MB | 3 GB | 0 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.