Moonshot open-sources Kimi K3.1 Pro weights, architecture hinted as Gated DSA
HanGuo97 · x · 2026-11-05
Moonshot AI's Kimi officially released the model weights of Kimi K3.1 Pro, continuing its open-intelligence push. Researcher yzhangcs commented "Gated DSA" on the release, hinting the model may use a gated sparse attention-style architecture — unconfirmed details. The RT was shared by Han Guo.
Related event: Moonshot AI Open-Sources Kimi K3.1 Pro with 2.8T Parameters(30 posts)→
More from Models
- SkyPilot Tokens lists Kimi K3.1 Pro day-0: 2.8T params, 1M context, 40% cheaper — skypilot_org · 2026-11-05
- New open-source American LLM pretrained from scratch teased, drawing AI community buzz — annadgoldie · 2026-11-05
- OpenAI October dev roundup: Decisions API, 12-hour caching, 8x faster Codex tokens — OpenAIDevs · 2026-11-05
- Researcher laments the enormous cost of RL used to squash models' quirky behaviors — generativist · 2026-11-05
- Gemini 4 C arbon one-shots 4,000-line demo, users say Google fixed model laziness — theREALmarvin · 2026-11-05
- DeepSeek alone handled 53% of OpenRouter's 27T daily tokens; open-weights labs top 75% — Comfortable-Rock-498 · 2026-11-05