advimman · First MLX build 24 Jun 2026

lama

MLX Image apache-2.0

A 51M parameter image to image model from advimman, with 2 MLX builds, from bf16 to fp32.

Hugging Face

Memory

Will it fit?Needs about 3 GB at bf16

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.

Terminal · Hugging Face CLI

$ pip install -U huggingface_hub
$ hf download mlx-community/LaMa-bf16

2 on mlx-community

Click a column to sort. Smallest size and most downloads are highlighted.

LaMa-bf16	bf16	102 MB	3 GB	0
LaMa-fp32	fp32	204 MB	3 GB	0

Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.