Transparency signal for adopters, based on public metrics — NOT a quality score:
• Adoption: 11.1k GitHub stars (public metric)
• Maintenance: last push ~9 months ago
• Openness: weights + code fully public (open licence)
• Docs: official model card, blog, HF hub
Most of this number is GitHub stars. See /methodology/#scoring.
⚠️ Red Flags & Trade-offs (AMI)
- A 1T-parameter MoE is not a laptop model — even quantised it needs serious GPU memory; it targets datacentre and cluster deployment. [Model card]
- Its headline strength is agentic coding and tool use; for plain chat it is heavier and slower than smaller models, and long-horizon agent runs burn many tokens. [GitHub]
- Released open-weight in Jul 2025; the ecosystem, third-party tooling and fine-tunes are newer and less battle-tested than DeepSeek or Qwen. [GitHub]
Each flag links to its primary source. See our Correction Policy.
📝 Report a correction or complaint
Corrections and complaints go straight to our editorial queue — read and actioned by the site operator, not lost in an inbox. No email needed.
Moonshot AI's 1T-parameter open-weight MoE (32B active) built for agentic coding and tool use — the open model that retook the global open-source lead in mid-2025.
11.1k stars · 912 forks · last push Jan 2026
💡 Lighter Alternatives (If this is too heavy)
Disclaimer
Red Flags and the AMI score are editorial analysis, not endorsements. They are produced with AI assistance and reviewed by a human, but are not a substitute for reading the primary source. The Adoption & Maintainability Index (AMI) reflects public adoption and availability signals only — never a verdict on the science, the code quality, or the people behind a project. We are not affiliated with any lab, university, or company named on this page, and links point only at primary sources (papers, repositories, journals). Content is informational and not engineering, business, or investment advice.