view post Post 1336 Qwen3.6 MTP is here! Run locally on 20GB RAM. ⚡️MTP enables Qwen3.6 to generate ~1.4–2.2× faster with no accuracy change.Qwen3.6-27B: unsloth/Qwen3.6-27B-MTP-GGUFQwen3.6-35B-A3B: unsloth/Qwen3.6-35B-A3B-MTP-GGUFGuide: https://unsloth.ai/docs/models/qwen3.6#mtp-guide See translation 👍 8 8 🔥 4 4 🤗 3 3 🚀 3 3 ❤️ 1 1 🧠 1 1 😎 1 1 + Reply
CohereLabs/command-a-plus-05-2026-w4a4 Image-Text-to-Text • 126B • Updated about 11 hours ago • 2.13k • • 172
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration Paper • 2605.20025 • Published 4 days ago • 112
Running 345 Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P 🔥 345 This Space uses ''HauhauCS/Gemma-4-E4B-Uncensored-Hauh...''.
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction Paper • 2604.27393 • Published 23 days ago • 72
Running on Zero Agents 31 Granite 4.0 1B Speech 🎧 31 Granite 4.0 1B Speech recognition and translation demo