view post Post 4075 Kimi K3 can now be run locally! ✨The 1-bit model retains ~78.9% accuracy after we shrunk it from 1.56TB to 594GB (-62% size).Run on a Mac Studio connected with 128GB RAM device. Kimi K3 is the strongest open model to date.GGUF: unsloth/Kimi-K3-GGUFGuide: https://unsloth.ai/docs/models/kimi-k3 See translation 5 replies · ❤️ 11 11 🔥 9 9 👍 3 3 🤗 1 1 + Reply
view article Article Accelerating Qwen3.6 on Intel® Core™ Ultra Series 3 with DFlash ofirzaf • 11 days ago • 11
view article Article NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics nvidia • 15 days ago • 63
view article Article Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident +2 hlarcher, XciD, raphael-gl, chris-rannou • 15 days ago • 456
view article Article Hugging Face on AMD Instinct MI455X: First Transformers Results badaoui • 18 days ago • 18
view article Article Be Ready Before the Attack: A Practical Guide to Self-Hosting an Open Model for Cyber Defense jeffboudier • 21 days ago • 20
view article Article NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval nvidia • 25 days ago • 58
view article Article Welcome Inkling by Thinking Machines +3 burtenshaw, merve, pcuenq, ariG23498, andito • 27 days ago • 161
view article Article Deploy GLM-5.2-FP8 as your open, frontier-level agent juanjucm • 28 days ago • 8