Forge
Forge is a web-based developer tool that allows users to run and test various open source machine learning models directly inside the browser using WebGPU and local GPU acceleration. It supports image segmentation, background removal, object detection, speech recognition, image classification, and text generation entirely client-side. The architecture ensures that media and text processing tasks run locally without sending data to external servers, providing an offline-capable playground for experimenting with models like Whisper, Qwen, and SegFormer.
Checked on Nov 2, 2026.
Alternative resources
High-performance in-browser language model inference engine leveraging WebGPU for hardware acceleration without server-side processing.
Run open-source LLMs directly in your browser using WebGPU for client-side local inference without external server dependencies.
Run open-source large language models locally or via cloud infrastructure with API integration for coding agents and development workflows.