OSAIM
ModelsFamiliesBy TaskBy SizeLicensesLeaderboardsCompareGlossary
Open Source AI Models

Moonshot AI

Kimi

Beijing-based lab founded by ex-Tsinghua researchers. Kimi K1.5 and K2 push very long context and reasoning; K2 is a trillion-parameter MoE with strong tool-use behaviour.

Visit homepage ↗

Flagship model

Kimi K2 Instruct
1000B

Moonshot AI's 1-trillion-parameter mixture-of-experts (32B active per token). Trained on 15.5T tokens with a heavy emphasis on tool-use and agentic behaviour. Modified-MIT licence with an attribution clause for very-large deployments. Exceptional at long-horizon agent tasks; benchmarked well against Claude Sonnet on SWE-bench Verified.

Context
128K
License
kimi
VRAM Q4
600 GB

1 model in this family

Kimi K2 Instruct
1000B

Moonshot AI's 1-trillion-parameter mixture-of-experts (32B active per token). Trained on 15.5T tokens with a heavy emphasis on tool-use and agentic behaviour. Modified-MIT licence with an attribution clause for very-large deployments. Exceptional at long-horizon agent tasks; benchmarked well against Claude Sonnet on SWE-bench Verified.

Context
128K
License
kimi
VRAM Q4
600 GB
Comparing Kimi against another family? Try the side-by-side comparator or browse all leaderboards.