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)→
More from Models
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11