Skip to content

Docling

docling-project/docling-layout-heron

Document-layout object detection with RT-DETRv2.

Start this recipeView on Hugging Face
Model metadata
CategoryDetectionParamsInformation unavailableContextInformation unavailableBackendsCUDA, METALTasksVision, Detection
Recipe authorship · Recorded configuration verification

Recipe authorship: Curated

Curated and generated describe how this recipe was written, not whether it ran successfully.

Recorded configuration verification

No current matching configuration verification record.

Records cover the tested default configuration on the named hardware. Matching release minor, variant, and rendering hash are required; changing options does not verify the new configuration.

Choose your actual device. Your browser cannot detect GPU memory.

Command builder

Hardware
Variant

mlx-community/docling-layout-heron-mlx-bf16

Mode: Detect
Advanced
Features
This feature is not available in the selected mode.
Memory estimation: Why unavailable?

This feature is not available in the selected mode.

Estimated memory use

approx

Approximate memory allocation in GB. These estimates are not measured peak usage.

  • Weights: ≈ 0.0 GB
  • KV: ≈ 0.0 GB
  • Drafter: ≈ 0.0 GB
  • Runtime allowance: ≈ 1.0 GB

Estimated to leave ≈ 9.7 GB of the ≈ 10.7 GB available memory.

Next: prepare the executable

Notes

  • Memory estimates are approximate because docling-project/docling-layout-heron geometry is incomplete.
  • Parameter count is unavailable, so the memory fit is approximate for docling-project/docling-layout-heron.
  • bf16 weights run as f16 on Apple Silicon.
  • This tier is estimated from nearby measurements.

1. Install

Install in your terminal. Uncached model IDs download automatically on first use.

MLXCEL_INSTALL_DIR="${MLXCEL_INSTALL_DIR:-$HOME/.local/share/mlxcel}" \
  && mkdir -p "$MLXCEL_INSTALL_DIR" \
  && curl -fL -o "$MLXCEL_INSTALL_DIR/mlxcel.zip" https://github.com/lablup/mlxcel/releases/download/v0.8.1/mlxcel-macos-aarch64.zip \
  && unzip -o "$MLXCEL_INSTALL_DIR/mlxcel.zip" -d "$MLXCEL_INSTALL_DIR/mlxcel-macos-aarch64" \
  && export PATH="$MLXCEL_INSTALL_DIR/mlxcel-macos-aarch64:$PATH" \
  && mlxcel --version
Installation and download help

Run the install command in your terminal. The selected executable should then be available on PATH. If it is not found, repeat the displayed PATH export in the same terminal.

Model IDs download automatically when first used. The optional download command prepares the checkpoint ahead of time. Uncached models require internet access and enough disk space; gated models also require access approval and credentials.

2. Run

Run this command in the same terminal after preparation. For server modes, keep it running and wait for the listening/ready message. If memory is insufficient, select a smaller checkpoint or reduce context/concurrency in advanced settings.

Copy all includes the selected installation, checkpoint download, and displayed run commands, in that order. Run them in the same shell; multi-node commands belong on their respective machines.

mlxcel detect

mlxcel detect -m mlx-community/docling-layout-heron-mlx-bf16 -i photo.jpg --threshold 0.3 --format json
Command flag help
-m
Selects the model or checkpoint repository.
-i
Sets an input path.
--threshold
Sets detection confidence threshold.
--format
Chooses output format.

3. Check the first result

For command-line modes, inspect the terminal output or the output file named by the command. Text generation returns text; embeddings/reranking return vectors or scores; audio/vision tasks return their task-specific transcript, audio, or detections.

Performance evidence

No benchmark is recorded for this selected checkpoint and hardware combination. Commands and memory estimates use the catalog's model information.

Memory fit is a model-based estimate, separate from measured throughput and successful inference verification.

No measurement is available for this hardware yet. See the family page for related profiles. Family

Prerequisites

  • Install the mlxcel build for your selected hardware and check the selected checkpoint's memory estimate.
  • Allow internet access and enough disk space to download an uncached checkpoint; obtain Hugging Face access approval when the checkpoint requires it.

Recipe options

  • • Detection returns bounding boxes and labels, not generated text.

Family

RT-DETRv2

Detection

Sibling recipes

pending

Guide

Docling Layout Heron

Docling Layout Heron detects document regions with RT-DETRv2. Detection is a CLI workflow and returns structured boxes and labels rather than generated text.

mlxcel detect -m mlx-community/docling-layout-heron-mlx-bf16 -i photo.jpg --threshold 0.3 --format json

The builder intentionally omits API snippets for detection because mlxcel currently exposes this workflow through mlxcel detect.

References