Meituan's LongCat-2.5: 1.6T-param multimodal agentic model with 48B active
Div_pradeep · x · 2026-11-05
Meituan released LongCat-2.5, a natively multimodal agentic model with 1.6T total parameters (48B active), built for long-horizon agentic tasks with stronger visual understanding and agentic coding for complex and visual coding work. Commenters highlight its systems engineering: images handled as discrete tokens unified in the main backbone, plus train-inference numerical alignment and W4A4 quantization for MoE.
Related event: Meituan Releases LongCat-2.5, a 1.6T-Parameter Multimodal Agent Model(2 posts)→
More from Models
- Qwen3.5-0.8B 'weight-space programming' finetune trends on Hugging Face — RikiyaT · 2026-11-05
- Hugging Face launches ML Intern, an open-source agent that does ML for you — Gradio · 2026-11-05
- ChatGPT, Claude and Gemini all meter usage now — none tells you what one message costs — Ok_Negotiation_2587 · 2026-11-05
- Jot: Google engineer's free open-source Mac dictation app powered by Gemini 3.5 Transcribe — bigaiguy · 2026-11-05
- Deep Principle open-sources Hydrogen 1.0 science model: GLM-based, 1M context, MIT — amaarora · 2026-11-05
- Tencent's Hy4 lands on Vercel AI Gateway at 50% off through end of 2026 — TencentHunyuan · 2026-11-05