Skip to content
AI News HubLIVE
More
Summary only

Meituan Releases LongCat-2.0: A 1.6T-Parameter Open MoE Model with Native 1M Context and LongCat Sparse Attention

Meituan has released LongCat-2.0, a 1.6 trillion-parameter Mixture-of-Experts model that activates about 48 billion parameters per token. It pairs a native 1-million-token context, built on LongCat Sparse Attention, with training and serving run end-to-end on domestic AI ASIC superpods. This article covers the architecture, vendor-reported benchmarks, API access path, and what remains unverified.

SourceMarkTechPostAuthor: Asif Razzaq
Meituan Releases LongCat-2.0: A 1.6T-Parameter Open MoE Model with Native 1M Context and LongCat Sparse Attention
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • LongCat-2.0 has 1.6T total parameters, dynamically activating 33B–56B per token.
  • It features a native 1M-token context window using LongCat Sparse Attention, reducing long-context cost from quadratic to linear.
  • Training and inference ran on a 50,000-card domestic AI ASIC cluster with no Nvidia hardware.
  • Vendor-reported benchmarks: 59.5 SWE-bench Pro, 70.8 Terminal-Bench 2.1, 77.3 SWE-bench Multilingual.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Agents