Moonshot releases Kimi K3 weights, a 2.8T MoE model with 1M context
teortaxesTex · x · 2026-07-28
Kimi releases Kimi K3 weights and technical report
Moonshot says Kimi K3 is its most capable model yet: a 2.8T MoE model with native visual understanding and a 1M-token context window.
The company highlights a new architecture it claims delivers 2.5x more intelligence per unit of compute, not just more parameters. It is also opening up more of the stack around the model, including:
- high-performance attention kernels
- an MoE communication library
- infrastructure for running agent environments at scale
The release includes the model weights, a technical report, and a tech blog.
Related event: Moonshot AI Releases Open-Weight Kimi K3 Model(43 posts)→
More from Models
- Moonshot’s Kimi K3 uses a MIT-like but non-commercial license — basedjensen · 2026-07-28
- k3 adds no RL algorithm changes, while tool-call steps track eval scores almost 1:1 — stochasticchasm · 2026-07-28
- DeepInfra adds Claude Opus 5 with 1M context and $5/$25 pricing — gharik · 2026-07-28
- Why a better benchmark score may still feel like a weaker model in practice — robleclerc · 2026-07-28
- Kimi K3 goes live on OpenRouter as third-party providers race to add support — scaling01 · 2026-07-28
- Kimi K3 arrives on Applied Compute for training and inference — rhythmrg · 2026-07-28