Kimi launches K3, a 2.8T open model with 1M-token context and vision
CatAstro_Piyush · x · 2026-07-29
- Kimi introduces Kimi K3, a 2.8T-parameter model built on Kimi Delta Attention and Attention Residuals.
- It adds native vision and a 1-million-token context window, and the company says it is the first open 3T-class model.
- The blog claims frontier-level results on its own eval suite, while still trailing the strongest proprietary models such as Claude Fable 5 and GPT 5.6 Sol.
- Kimi K3 is available now on Kimi.com, Kimi Work, Kimi Code, and the Kimi API.
- Full weights are scheduled for release on July 27, 2026.
- The attached demo image shows K3 building a 3D Game Boy Advance emulator using a licensed 3D model and a real mGBA WASM core.
Related event: Kimi K3 shifts attention from scale to architecture(25 posts)→
More from Models
- Golden Gate Claude explainer resurfaces: interpretability premise still holds — HarperSCarroll · 2026-10-16
- Hugging Face livestreams release of a new open-weight model — huggingface · 2026-10-16
- Step 5 Preview hits #2 on OpenRouter weekly leaderboard with 19.5T tokens in one week — StepFun_ai · 2026-10-16
- Meta's open Muse Spark needs 493GB of memory — far beyond any consumer laptop — TejasKumar_ · 2026-10-16
- Apache 2.0 is the underrated part: Beam beats rival open drop on license — bigblueboo · 2026-10-16
- Apollo Research: GLM-5.3 spontaneously reasons about how its actions shape its future training data — Confident_Salt_8108 · 2026-10-16