Skip to content
Other

YOLO11n DocLayNet

compact document layout analysis model

2 min readupdated

YOLO11n DocLayNet is a lightweight AI model built on Ultralytics YOLO11 (packing just 2.6M parameters) designed to detect structural elements across document pages. It identifies text, tables, headings, formulas, images, and other layout blocks in PDFs and scans. Despite its tiny footprint, it outperforms the larger standard YOLO11s model on the DocLayNet benchmark. Combining high accuracy with modest hardware requirements, it is a solid fit for developers building automated data extraction and document parsing pipelines.

Key features

  • Compact YOLO11n architecture with 2.6M parameters that outperforms YOLO11s.
  • Supports 11 layout categories, including text, tables, headings, formulas, and footers.
  • High accuracy of 0.760 mAP50-95 on the DocLayNet test dataset.
  • Optimized for processing document pages at 1024px resolution.

What you can do

  • Automatically parse layouts of research papers, financial reports, and patents.
  • Integrate the model into OCR and PDF content extraction pipelines.
  • Export weights to ONNX format for faster inference.

Example

from huggingface_hub import hf_hub_download
from ultralytics import YOLO

model = YOLO(hf_hub_download("avbiswas/yolo11n-doclaynet", "yolo11n-doclaynet.pt"))
results = model.predict("page.png", imgsz=1024, conf=0.25)
for box in results[0].boxes:
    print(model.names[int(box.cls)], float(box.conf), box.xyxy.tolist())
Read moreDetails
Benchmark: 0.760 mAP50-95 across 2,500 DocLayNet pages.
Training: 22 epochs on a single A100 using a 69k-page dataset.
Limitations: slides, forms, and handwritten text are not supported.
License: AGPL-3.0 (inherited from Ultralytics).
Discuss Telegram 0 68

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.0 GB · ready files0.5 GB
  • FP8 / INT8recommendedweights 0.0 GB0.5 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # avbiswas/yolo11n-doclaynet
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download avbiswas/yolo11n-doclaynet --local-dir ~/models/yolo11n-doclaynet
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to yolo11n-doclaynet
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of yolo11n-doclaynet (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

avbiswas/yolo11n-doclaynet
Author
avbiswas
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

680

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments