Data checked 2026-08-13. Data may be stale - beyond the review cycle.
Review cycles are documented on the Methodology page. Methodology
PINTO0309/PINTO_model_zoo
Software Tool Tier A edge_ai MIT
A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.
Engineering Snapshot
Use cases & tasks 6
- Best suited for
-
- Edge AI developers targeting multiple runtimes
- Teams benchmarking model performance across frameworks
- Rapid prototyping on EdgeTPU, CoreML, OpenVINO, TensorRT
- Primary tasks
-
- Cross-framework model format conversion
- Edge deployment model sourcing
- Multi-target model optimization (INT8, FP16, FP32)
Stack & ecosystem
- Resource type
- Software Tool
- Ecosystem
- caffe · computer-vision · coreml · edgetpu · keras · mediapipe
License & compliance
- License
-
MIT(Inferred)
Lifecycle & freshness Show
- Maintenance
- Active
- Latest version
- Not recorded
- Last activity
- 2026-08-13
- Last checked
- 2026-08-13
- Verification
- Official confirmed
What It Solves
Engineers need pre-converted models across multiple frameworks (TensorFlow, PyTorch, ONNX, OpenVINO, TensorFlowLite, EdgeTPU, CoreML, TFTRT, TFJS) to deploy on diverse edge hardware without manual conversion.
Primary use cases
- Cross-framework model format conversion
- Edge deployment model sourcing
- Multi-target model optimization (INT8, FP16, FP32)
Secondary use cases
- Model zoo for computer vision tasks (MediaPipe, Keras, Caffe)
- Reference for conversion scripts and workflows
When to Use
Consider when
- Target hardware requires specific runtime (EdgeTPU, CoreML, OpenVINO)
- Need models in multiple formats simultaneously
- License compatibility of individual models must be verified
Verify before adopting
- Individual model licenses (repo MIT, but models may differ)
- Conversion accuracy for quantized variants (INT8/FP16)
- Framework version compatibility with target runtime
Start Here
Adoption Checklist
- Needs verification Individual model licenses (repo MIT, but models may differ)
- Needs verification Conversion accuracy for quantized variants (INT8/FP16)
- Needs verification Framework version compatibility with target runtime
Each check stays "needs verification" until an official source confirms it; unconfirmed items are never marked verified.
Known Limitations & Unknowns
Known limitations
- No explicit hardware targets listed in metadata
- Conversion quality varies by model and quantization
- Single maintainer (PINTO0309) - bus factor risk
- Model coverage limited to computer vision domain
Not publicly verified
- Update frequency for new framework versions
- Coverage of specific architectures (YOLO, MobileNet, etc.)
- Automated testing of converted models
Alternatives & Related Tools
Related tools
- onnx-runtime — Integrates with
- openvino — Integrates with
How is it used?
Start from the recorded entry points below, then validate against the technical checklist.
- Official site https://qiita.com/PINTO
- Repository https://github.com/PINTO0309/PINTO_model_zoo
- Documentation https://qiita.com/PINTO
Technical checklist
- OK License identified Recorded: MIT
- OK Maintenance signal Active
- OK Verification status Official confirmed
- OK Source evidence attached 1 source record(s)
- NEEDS REVIEW Latest version recorded Not recorded
Official Links
Metadata & Governance
| License | MIT — Inferred |
|---|---|
| Commercial model | Unknown |
| Maintenance status | Active |
| Verification status | Official confirmed — Confirmed via the official repository API responses in SourceRefs below. |
| Latest version | Not recorded |
| Latest release | Not recorded |
| Last activity | 2026-08-13 |
| Last checked | 2026-08-13 |
| First seen | Not recorded |
Dataset facts
Facts above come from the official dataset card only; unconfirmed fields stay unknown.
Related Resources & Dependencies
- onnx-runtime — integrates with (confirmed)
- openvino — integrates with (confirmed)
Recent Activity
New resource: PINTO0309/PINTO_model_zoo
New repository resource added by the sprint promote pipeline.
Related Knowledge
Guides
- Deploying AI Inference on UAV Edge Compute — A repeatable workflow for choosing and validating an inference runtime for an onboard UAV computer.
Collections
- Edge AI Perception Starter — A starting stack for prototyping aerial perception models before edge deployment work.