Leaked Kimi K3 Configuration Rumors

burny_tech · x · 2026-07-14

Rumors suggest Kimi K3 might launch tomorrow with top-up discounts. The leaked info hints at a suspected configuration: 6:1 linear attention, DSA for global attention, 70 layers, 1 million context length, 1.5T parameters, roughly 30T training tokens, latent MoE (or a variant), Kimi residual attention, no engram, and native multimodality (though currently text-output only).

However, the poster explicitly stated they "have no information," making this an unverified leak based on a briefly public page rather than an official announcement.

Related event: Kimi K3 hype builds as KIVINE appears on Arena(43 posts)→

Original post →

More from Models

Models channel →