view article Article MiniMax Goes Sparse: Decoding M3's Attention from a Single Diagram AtlasCloud-AI • about 1 month ago • 10
💻 Qwopus-Coder Collection Reasoning-distilled coding models optimized for specialized domains like agentic workflows. • 7 items • Updated 14 days ago • 25
🚀 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. • 8 items • Updated 9 days ago • 29
🍎 Qwopus3.6 Collection This collection features the advanced Qwopus3.6 series of multimodal large models, which are fine-tuned from the Qwen3.6 base models with a focus on e • 10 items • Updated May 23 • 70
Gemopus-4 Collection 🪐 A curated collection of lightweight multimodal Gemopus-4 models designed for edge deployment. • 6 items • Updated May 23 • 17
Qwopus3.5-v3.5/v3 Collection 🌟Qwopus3.5-v3.5 is the latest model in the Claude series. • 14 items • Updated May 23 • 106