Browser AI and WebAssembly
Run and optimize AI workloads in the browser with WebLLM, Transformers.js, WebGPU, and WebAssembly.
Recommended tools
Image OCR
Chinese/English text recognition (Tesseract.js). 100% free, runs locally in your browser—nothing is uploaded to our servers.
AI Token Counter
Estimate token count for GPT-4/GPT-3.5/Claude models. 100% free, runs locally in your browser—nothing is uploaded to our servers.
Text to Speech
Read text aloud using browser SpeechSynthesis API.
Image Compress
Batch compress to WebP/JPG/PNG with max dimension and quality controls. 100% free, runs locally in your browser—nothing is uploaded to our servers.
Guides and analysis
Running LLMs in the Browser: WebLLM, Transformers.js, and ONNX Runtime Web in 2026
A comprehensive guide to running large language models directly in the browser. Covering WebLLM, Transformers.js, and ONNX Runtime Web with architecture, benchmarks, and production deployment strategies.
Edge AI Inference Deployment: 5 Production Patterns from Model Compression to Wasm Runtime
Complete guide to edge AI inference deployment covering model compression, ONNX Runtime, WasmEdge AI inference, edge-cloud collaboration, and production monitoring with full Python/Rust/C++ code
Rust + WebAssembly Edge AI Inference with WasmEdge Runtime
From compiling Rust to Wasm to WasmEdge runtime deployment, a hands-on guide to building edge AI inference services with WASI-NN interface and optimization strategies
WebGPU Compute Shaders: Browser GPU Computing Guide and Optimization
Deep dive into WebGPU Compute Shaders, covering WGSL shader language, compute pipelines, workgroup dispatch and browser GPU computing practices
How WebAssembly Is Reshaping Browser-Side Compute: From FFmpeg.wasm to OxiPNG
A deep dive into running native C/Rust in the browser via WebAssembly, with real-world performance and architecture lessons from FFmpeg.wasm video transcoding and OxiPNG image compression.