Transparency signal for adopters, based on public metrics:
• Adoption: 104.7k GitHub stars (public metric)
• Maintenance: last push ~14 months ago
• Openness: weights + code fully public
• Docs: official README, deploy recipes
Not a rating of the science.
⚠️ Red Flags & Trade-offs (AI Verified)
- The 671B MoE needs roughly 350–411GB of VRAM even at INT4 — no consumer GPU runs it; multi-GPU or a server cluster is mandatory. [Model card]
- It is a base model with no instruction tuning by default; using it as a chatbot requires your own SFT / post-training. [README]
- The official API routes traffic through servers under Chinese data-law jurisdiction, making HIPAA / GDPR enterprise compliance a hard gate. [DeepSeek API docs]
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.
671B Mixture-of-Experts LLM — the open model that put DeepSeek on the global map, with strong multilingual performance.
104.7k stars · 16.7k forks · last push Aug 2025
💡 Lighter Alternatives (If this is too heavy)
Disclaimer
Red Flags and the AI 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. Scores reflect 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.