weights land nov 4, but this wont be a local model for most of us.
2.8T params is ~1.4 TB of memory at 4-bit, just for the weights.
104B active makes it fast, not small. the real win is that anyone can host it, so you're not stuck with one provider's limits.
Kimi.aiX
View on XIntroducing Kimi K3.1 Pro: our most capable 3T-class open-weight model.
🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal.
🔹 Full-project coding: games in Unreal, Unity & Godot.
🔹 Excels at parametric 3D modeling in Blender & CAD.
🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%.
🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks.Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on http://kimi.ai/, Kimi Work, Kimi Code, and the Kimi API.
Open weights by Nov 4, 2026.
🔗 API: http://platform.kimi.ai/
🔗 Tech blog: http://kimi.ai/blog/kimi-k3-1-pro