# Meituan LongCat Team Open Sources LongCat-2.5

- Category: Flash (快讯)
- Published: 2026-11-10T12:00:00.000Z
- Source date: 2026-11-10
- HTML: https://www.88z.ai/en/news/flash-20261110-6a64b40110a6cc65
- Markdown: https://www.88z.ai/en/news/flash-20261110-6a64b40110a6cc65.md
- Other language: https://www.88z.ai/news/flash-20261110-6a64b40110a6cc65.md

Meituan's LongCat team has open-sourced the LongCat-2.5 model under the MIT license, allowing commercial use. With 1.6 trillion total parameters and approximately 48 billion activated, it supports million-token contexts and long-horizon agent tasks. Optimized for domestic computing power, it significantly improves single-card training throughput.

## At a glance

- LongCat-2.5 is open-sourced under MIT license, supporting million-token contexts and long-horizon agent tasks
- Optimized for domestic computing power, achieving 86% higher single-card SFT throughput than DDP

## The update

The LongCat team under Meituan has officially open-sourced the LongCat-2.5 model. Released under the MIT license, it fully supports commercial inference and further training. The model features 1.6 trillion total parameters with approximately 48 billion activated, capable of handling million-token contexts and designed specifically for long-horizon agent tasks. Technically, it employs W4A4 quantized inference and is deeply optimized for domestic computing hardware. It enables long-sequence training even when single-card memory is under 80GB. Tests show that its supervised fine-tuning (SFT) single-card throughput is 86% higher than distributed data parallel (DDP) methods, effectively lowering deployment and training barriers.

## Sources

- [龙猫LongCat](https://mp.weixin.qq.com/s/EGLDrPxND-xGTyStJIDXrw) (2026-11-10)

This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.