LongCat AI – Next-Generation Multi-Modal Models
Open-source MoE LLMs by Meituan: Flash-Chat, Flash-Thinking, Video, Image (generation & editing), Audio-Codec, and Omni. Fast, efficient, and production-ready.
Latest Release: LongCat-Image
Meituan LongCat releases and open-sources LongCat-Image, a 6B parameter AI image generation and editing model. Through high-performance architecture design, systematic training strategies, and data engineering, it achieves performance comparable to larger models, providing developers and industry with a "high-performance, low-threshold, fully open" solution.
Open-source SOTA achievements: Image editing (GEdit-Bench 7.60/7.64, ImgEdit-Bench 4.50), Chinese text rendering (ChineseWord 90.7, covering all 8,105 standard Chinese characters), and competitive text-to-image performance (GenEval 0.87, DPG-Bench 86.8). Available on LongCat Web and LongCat APP (24 templates, image-to-image).
✨ Integrated Generation & Editing
- Simple prompts, high-quality output: Deep semantic understanding enables simple prompts to generate highly aligned images.
- 15 editing task types: Object add/remove, style transfer, perspective change, portrait refinement, text modification — all with natural language.
- Multi-round editing without quality loss: Maintains style, lighting, and consistency; preserves facial features in portraits.
✨ Superior Chinese Text Rendering
- High-quality character rendering: Accurate text in shop signs, posters, book covers, and natural scenes (Chinese and English).
- Rare character support: High accuracy for uncommon characters, variant forms, and calligraphy styles (Kai, Xing).
- Smart typography: Automatically matches scene context for font size, color, and spacing.
✨ Studio-Quality Output
- Fast generation: Lightweight optimization enables efficient high-resolution image generation.
- Photography-grade quality: Optimized composition and lighting; accurate textures and realistic proportions.
Model Series
Image
6B parameters | Open-source SOTA on image editing (GEdit-Bench, ImgEdit-Bench) and Chinese text rendering (ChineseWord: 90.7). Covers all 8,105 standard Chinese characters.
Latest Release | Hugging Face | GitHub
Flash-Thinking
Enhanced reasoning with dual-path framework. 64.5% token savings in agentic scenarios.
Released: Sept 22, 2025
Flash-Chat
Foundation dialogue model (560B params, MoE). Achieves 100+ tokens/s on H800 GPUs with ~27B active params/token.
Released: Sept 1, 2025
Key Highlights
- High-throughput inference: 100+ tokens/s on H800 GPUs
- Zero-Computation Experts: Activates only ~27B params/token from 560B pool
- Extended context: Up to 128K tokens
- AI image generation: Fast, studio-quality image generation and editing with superior Chinese text rendering
- Open-source SOTA: Leading performance on Omni-Bench, WorldSense, MMLU, and more
- Production-ready: Deployed across Meituan's services