Kimi K3 with 2.8T parameters and 1M context now supported on vLLM
ricklamers · x · 2026-07-27
vLLM announces Day-0 support for Moonshot AI's Kimi K3, one of the most powerful open-weight models. K3 features 2.8T parameters (MoE, 16/896 experts active), 1M context window, native multimodal understanding including vision, and Kimi Delta Attention (hybrid linear and full attention) for affordable long context. Thanks to partners Moonshot, inferact, NVIDIA, AMD.
Related event: vLLM brings day-0 support to Moonshot’s Kimi K3(11 posts)→
More from Models
- theo builds his own visualizer for today's agent models, showing how cheap Luna really is — ivan_bezdomny · 2026-09-23
- Why ChatGPT Still Wins: One User's Split Between Muse, Claude and Codex — mobileraj · 2026-09-23
- Muse reportedly offers 4B tokens/week for ~$100/month, sparking industry price-disruption talk — NewYak4281 · 2026-09-23
- GPT-6 Sol and Luna appear in OpenAI docs, alongside guidance on reasoning effort — cedric_chee · 2026-09-23
- GPT-6 tested on LIBERO robot task: turns on stove, fails to grasp moka pot — YuXiang_IRVL · 2026-09-23
- Ternary Bonsai 2 27B: 5.9GB weights retain ~95% of full-precision reasoning — cephaloform · 2026-09-23