docling-project · First MLX build 17 May 2026
docling-layout-heron-101
MLX
Vision apache-2.0
A 77M parameter object detection model from docling-project, with one MLX build at bf16.
- Parameters
- 77M From Hugging Face
- Quantisation
- bf16 docling-layout-heron-101-mlx-bf16
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 153 MB Weights, estimated
- Downloads
- 23 This build, last 30 days
- Task
- Object detection Vision
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
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.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/docling-layout-heron-101-mlx-bf16MLX builds
1 on mlx-community| docling-layout-heron-101-mlx-bf16 | bf16 | 153 MB | 3 GB | 23 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.