Kimi K3 Weights Released: 93 Layers, Latent MoE Replaces Standard MoE
hugobowne · x · 2026-07-29
Kimi K3 weights dropped yesterday. Sebastian Raschka quickly analyzed the architecture:
- 93 layers (vs. 27 in Kimi Linear)
- Latent MoE replaces standard MoE
- Raschka's summary: "It's basically Kimi Linear, bigger, with latent MoE."
Full conversation at the video link.
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