Moonshot releases Kimi K3 weights, a 2.8T MoE model with 1M-token context
Gradio · x · 2026-07-29
- Moonshot released the weights and technical report for Kimi K3.
- Kimi K3 is described as the company’s most capable model: a 2.8T MoE system with native visual understanding and a 1M-token context window.
- Moonshot also says the model uses a new architecture that delivers 2.5× more intelligence per unit of compute, and it is opening more of the stack around it, including high-performance attention kernels, an MoE communication library, and infrastructure for running agent environments at scale.
- The repost also points to an open-source Hugging Face workflow for trying Kimi K3 without API keys.
Related event: Kimi K3 shifts attention from scale to architecture(25 posts)→
More from coding & agent
- Building a portable context vault in Notion so every AI agent knows you from day one — ivanhzhao · 2026-10-16
- Reflection AI open-sources Beam: 501B-param MoE model under Apache 2.0 for agentic coding — arena · 2026-10-16
- Deep Research API showdown: OpenAI, Perplexity, Parallel, Tavily, Gemini, Valyu compared — bar_raiser333 · 2026-10-16
- Geoffrey Huntley open-sources Overalls, a self-hosted AI developer platform under MIT — kieranklaassen · 2026-10-16
- Dev shows 199.7bn tokens over 200 days on OpenAI Codex, peak 8.6bn/day — Dimillian · 2026-10-16
- Ask Claude to open its changes in nvim and scroll to the exact line for review — max__drake · 2026-10-16