LongCat-Flash Technical Report

Zero-computation experts spend a token budget unevenly — 560B params, ~27B active, 100+ tokens/s.

Meituan LongCat Team · arXiv 2025 · Model Architectures. Read the paper ↗

A free, interactive, animated visual explainer of LongCat-Flash Technical Report — every exhibit computed from the real formulas, with verbatim quotes from the source.

Questions

What is LongCat-Flash Technical Report?

Zero-computation experts spend a token budget unevenly — 560B params, ~27B active, 100+ tokens/s.

Who published LongCat-Flash Technical Report, and where?

Meituan LongCat Team — arXiv 2025 (arXiv:2509.01322).

Where can I find a visual explainer of LongCat-Flash Technical Report?

Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.

Related explainers

• DeepSeek-V3
• Qwen3
• OLMo 2
• MiniMax-01
• Gemma 4
• Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• Scalable Diffusion Models with Transformers