LFM2.5 1.2B Thinking WebGPU
Run LFM2.5-1.2B-Thinking directly in your browser on WebGPU
A collection of demos built with Transformers.js V4
Run LFM2.5-1.2B-Thinking directly in your browser on WebGPU
Real-time speech transcription, entirely in your browser.
A compact reasoning-capable model running in your browser.
Run Qwen3.5 (0.8B, 2B, 4B) in-browser with Transformers.js
Run Cohere Transcribe locally in your browser on WebGPU.
Run GPT-OSS-20B locally in your browser on WebGPU
Real-time video captioning in your browser
Create cinematic video designs locally in your browser
Private browser-based translator with 56 languages
Chat with Nanbeige AI locally in your browser
Segment images with click points and download cutouts
WebGPU-accelerated Mixture of Experts
Real-Time Detection Transformers running in your browser
Run Olmo-Hybrid-7B 100% locally in your browser on WebGPU
Run granite-4.0-1b-speech on WebGPU with Transformers.js
TinyAya running locally in your browser with Transformers.js
Run QED-Nano locally in your browser with Transformers.js
Visualize sentence embeddings in an interactive scatterplot
Real-Time Detection Transformers running in your browser
A showcase of the Falcon-H1 architecture (Mamba + Attention)
Search documents semantically and view results in 3D carousel
Summarize webpages locally in your browser (demo)
Run Gemma 4 locally in-browser on WebGPU w/ Transformers.js