Reasoning Chat (DeepSeek-R1 Distill)
ReadyRun a reasoning LLM in-browser: watch it think step-by-step, then answer (DeepSeek-R1 / MiniThinky).
This demo loads a large model in your browser — the first run may take a while
Model size ~1.7 GB, please be patient while it loads
WebGPU not available — falling back to CPU (slower)
WASM（较慢）
WebGPU is not supported in this browser; falling back to WASM (slower, Chrome/Edge recommended).
The first run downloads the model (DeepSeek-R1-1.5B ~1.1GB / MiniThinky-1B ~700MB); please be patient.
Type a question to start chatting (load a model first)
Examples: