Skip to content
Other

MAAP3D ModelZoo

Model repository for animal detection and pose estimation

2 min readupdated

The MAAP3D ModelZoo repository contains pretrained models and configurations for bounding-box detection and keypoint pose estimation of various animals. The collection includes six pairs of pose configurations and checkpoints, as well as four detectors for species such as birds, primates, and corvids. All models are currently in draft status, and their inference has not yet been validated within this repository. The set will be useful for animal behavior researchers and developers using the MAAP3D and MMPose frameworks.

Key features

  • Six species groups: includes models for monkeys, birds, crows, tits, Siberian jays, and pigeons.
  • Configurations and checkpoints: provides weight files (such as .pt and .pth) and configuration scripts for MMPose.
  • Open-source licensing: models are distributed under the AGPL-3.0-or-later license for original MAAP3D contributions while preserving upstream project terms.
  • Standardized metadata: each model contains a JSON description with class names, joint lists, and weight paths.

What you can do

  • Apply for detection: use the detector files to locate birds or primates in images.
  • Estimate animal poses: apply top-down pose models (requiring prior bounding-box detection) for movement analysis in research.
  • Integrate into MAAP3D: load weights and configurations to work within a local MAAP3D environment.
  • Expand the model zoo: add custom weights and configurations according to the repository's metadata naming rules.

Example

The models use a file structure featuring a model identifier prefix, such as: pigeon-detection.pt for the pigeon detector, pigeon-pose.pth for the pose weights, and pigeon-pose.py for the MMPose configuration. Running them requires connecting local paths for the downloaded configuration and weight files within the MAAP3D environment.

Read more
Details
Contents: 6 pairs of pose configs and checkpoints, 4 detectors
Coverage: primates (chimpanzees, bonobos), corvids, pigeons, tits, jays
Status: draft, inference not validated by authors
Dependencies: detection boxes required for pose estimation models (top-down estimators)
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.1 GB · ready files0.7 GB
  • FP8 / INT8recommendedweights 0.1 GB0.6 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.

    # MAAP3D/ModelZoo
    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 MAAP3D/ModelZoo --local-dir ~/models/ModelZoo
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to ModelZoo
  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 ModelZoo (quants, finetunes, LoRAs) will show up under the bell.

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

About the model

MAAP3D/ModelZoo
Author
MAAP3D
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

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

Comments