🚀 Qwen-MTP Collection ⚡ MTP (Multi Token Prediction) speculative decoding enables models like Qwen3.6 to have ~1.4-2.2x faster generation with no change in accuracy. • 9 items • Updated 28 days ago • 34
MiniCPM-o & MiniCPM-V Collection Multimodal models with leading performance. • 32 items • Updated May 24 • 84
Running on CPU Upgrade Featured 151 Ostris' AI Toolkit 💻 151 Train FLUX, Qwen and Wan LoRAs with Ostris Ai Toolkit