Meituan open-sources LongCat-2.5: 1.6T total params, ~48B active, MIT license
victormustar · x · 2026-11-09
Meituan's LongCat team released LongCat-2.5, a natively multimodal agentic model, with weights on Hugging Face under MIT license.
- 1.6T total parameters, 48B active (MoE)
- Built for long-horizon agentic tasks, with stronger visual understanding and agentic coding
- Targets complex coding projects, visual coding like creative design, and 3D tasks
Another trillion-parameter MoE fully open-sourced by a Chinese company, purpose-built for agent workloads.
Related event: Meituan Open-Sources LongCat-2.5, a 1.6T-Parameter Multimodal MoE Model(2 posts)→
More from Models
- Claude Fable 5.5 needs a 70 on AA index to justify replacing Opus 5.5 — haider1 · 2026-11-09
- Leaked checkpoints suggest Google now ships a major Gemini release every month — lyraxana · 2026-11-09
- HF's Niels Rogge releases 'Getting Started with Local AI' slides: quantization, MoE, local agents — NielsRogge · 2026-11-09
- InstaDeep CEO: Anthropic's unreleased Models 3 and 4 sit halfway to AI2027's Agent-2 — connoraxiotes · 2026-11-09
- 27B open-weight decision model Drex Max takes #1 on Artificial Analysis Decision Index — dr_cintas · 2026-11-09
- JEV models get full support in Hugging Face transformers, now standardized — art_zucker · 2026-11-09