Running on Zero MCP 2.69k Z Image Turbo πΌ 2.69k Generate high-quality images from text prompts in seconds
Running on T4 Featured 15 FloodDiffusion Streaming Demo π 15 Streaming Motion Generation (CVPR 2026)
Running 22 Parayomi β γ΅γγγͺδΊζΈ¬γ’γγ« π 22 Generate furigana readings for Japanese text
Running Featured 61 Qwen3.5 WebGPU π» 61 Run Qwen3.5 (0.8B, 2B, 4B) in-browser with Transformers.js
Running Featured 57 Nemotron 3 Nano WebGPU β 57 A compact reasoning-capable model running in your browser.
view post Post 3821 Can small models program?Although even if they are reasoning AIs, small AIs cannot create extensive and high-quality code, at least that's what is commonly thought.We present OrionLLM/NanoCoder-0.6b, an AI with just 600 million parameters based on qwen3-0.6b and trained with the dataset nvidia/OpenCodeReasoning.While not good at complex code, we observed a significant improvement in code generation (especially in Python code), demonstrating that, when trained correctly, small AIs can, in fact, program. See translation 2 replies Β· π€ 9 9 π 1 1 π₯ 1 1 + Reply
Running Featured 84 Voxtral Realtime WebGPU π¬ 84 Real-time speech transcription, entirely in your browser.
Running on A10G Featured 191 faster-qwen3-tts π 191 Generate speech audio from text with custom or cloned voices