LFM2.5 1.2B Thinking WebGPU
💧
91
Run LFM2.5-1.2B-Thinking directly in your browser on WebGPU
Transformers.js V4 demos
A collection of demos built with Transformers.js V4
-
-
GPT OSS WebGPU
⚡64Run GPT-OSS-20B locally in your browser on WebGPU
-
Text Behind Video
🎥42Create cinematic video designs locally in your browser
-
Voxtral Realtime WebGPU
💬53Real-time speech transcription, entirely in your browser.
-
TranslateGemma 4B WebGPU
🌐35Private browser-based translator with 56 languages
-
SAM3 Tracker WebGPU
🎯30Segment images with click points and download cutouts
-
Qwen3.5 WebGPU
😻39Run Qwen3.5 (0.8B, 2B, 4B) in-browser with Transformers.js
-
LFM2 VL WebGPU
📹24Real-time video captioning in your browser
-
RF DETR Medium WebGPU
⚡16Real-Time Detection Transformers running in your browser
-
Olmo Hybrid WebGPU
🦙11Run Olmo-Hybrid-7B 100% locally in your browser on WebGPU
-
TinyAya WebGPU
🌍8TinyAya running locally in your browser with Transformers.js
-
QED-Nano WebGPU
✖6Run QED-Nano locally in your browser with Transformers.js
-
voyage-4-nano WebGPU
🚀4Visualize sentence embeddings in an interactive scatterplot
-
RF DETR Nano WebGPU
⚡3Real-Time Detection Transformers running in your browser
-
Granite 4.0 1b Speech WebGPU
🗣7Run granite-4.0-1b-speech on WebGPU with Transformers.js
-
Falcon-H1-Tiny-90M WebGPU
🦅2A showcase of the Falcon-H1 architecture (Mamba + Attention)