tract and microflow-rs
Both are TinyML inference engines supporting ONNX, making them competitors for resource-constrained embedded systems and other tinyML applications.
About tract
sonos/tract
Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
Implements graph-level optimization passes (constant folding, operator fusion, quantization-aware transformations) and supports symbolic dimensions for dynamic shapes, enabling efficient inference on resource-constrained embedded systems. Built in Rust with zero external dependencies, it provides both a standalone CLI and language bindings (Python, C) for framework integration. Handles ONNX (85%+ operator coverage), TensorFlow 1.x, and NNEF formats with a production-focused subset philosophy that excludes rarely-used features like tensor sequences in favor of maintainability and performance.
About microflow-rs
matteocarnelos/microflow-rs
A robust and efficient TinyML inference engine.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work