Back to News
Google•July 9, 2026
LiteRT.js
Free
Web AI
Machine Learning
LiteRT
JavaScript
### TL;DR
LiteRT.js is a high-performance web AI runtime that enables developers to run machine learning models directly in the browser. By leveraging WebAssembly and hardware acceleration like WebGPU and WebNN, it allows for low-latency, private, and serverless AI inference using .tflite models.
Key Insights & Metrics
Pricing
Free & Open-source
Cost structure
Version
N/A
Current release version
Hardware
A standard CPU, a WebGPU-compatible GPU, or a dedicated NPU, running on a modern, up-to-date web browser
Compute requirements
Category
Free
Licensing model
Region
United States
Primary region
Key Features
- Native hardware acceleration via XNNPACK (CPU), WebGPU (GPU), and WebNN (NPU)
- Seamless deployment of existing .tflite models in web applications
- Tailored quantization support via AI Edge Quantizer for optimized performance and model size
- Unified cross-platform runtime shared with LiteRT for Android, iOS, and desktop
- Integrated PyTorch conversion support through LiteRT Torch
Discussion
0
Upvotes
0
Downvotes
0 reviews
Sign in to leave a review
Reviews
No reviews yet. Be the first to review!