# onnx/models

A collection of pre-trained, state-of-the-art models in the ONNX format

Repository: https://github.com/onnx/models
Canonical: https://ross.abutalabs.com/products/onnx-models
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: onnx, models, download, pretrained, deep-learning
Last push: 2026-08-01T04:35:29+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 35, longevity 100
- inputs: {"age_days": 3254, "days_push": 32, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9773, forks 1584 (observed 2026-08-28T04:10:37.112609+00:00)

## What it is
The ONNX Model Zoo is a curated collection of pre-trained, state-of-the-art machine learning models in the ONNX format, covering vision, NLP, generative AI, and graph ML. The repository is now deprecated and preserved for historical purposes, with models migrated to Hugging Face.

## Use cases
- download pretrained onnx models for image classification
- find object detection models in onnx format
- get onnx versions of nlp models like translation
- run state-of-the-art models without training from scratch
- convert or use models across different ml frameworks

## When to choose
- you need validated pre-trained ONNX models for vision or language tasks
- you want framework-agnostic models runnable with ONNX runtimes
- you need historical reference for the ONNX model ecosystem

## When to avoid
- you need the latest models - use Hugging Face instead since LFS downloads ended July 2025
- you need actively maintained or newly contributed models
- you need training code rather than pre-trained weights

## Facets
- artifact type: dataset
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, nlp, speech-recognition
- domain: machine-learning, deep-learning, computer-vision, artificial-intelligence
- platform: cross-platform
- tags: onnx, pretrained-models, model-zoo, deprecated, hugging-face, natural-language-processing

## Member repositories
- onnx/models (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:37.112609+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:21:02.350671+00:00, confidence not recorded.
  - readme: https://github.com/onnx/models (fetched 2026-08-28T04:10:37.112609+00:00, sha 7edff33a2a12)
- Data as of 2026-08-30T08:39:29.467469+00:00.