Running 3 LFM2-350M WebGPU (custom WGSL kernels) 🔥 3 Chat with a 350M LLM directly in your browser
Running Falcon-Perception WebGPU (custom WGSL kernels) 🦅 Open-vocab detection on video, custom WGSL, in the browser
Running Falcon-Perception WebGPU (custom WGSL kernels) 🦅 Open-vocab detection on video, custom WGSL, in the browser
Running 3 LFM2-350M WebGPU (custom WGSL kernels) 🔥 3 Chat with a 350M LLM directly in your browser