meituan-longcat/LongCat-Flash-Chat resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1365 stars · 74 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

LongCat-Flash-Chat is the official repository for Meituan's LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) foundation language model with dynamic parameter activation (~27B average per token). The repo provides model weights, technical documentation, and inference guidance for this non-thinking chat model optimized for agentic tasks.

Use cases

• download and run a large open-weight MoE language model
• serve a chat model for agentic workflows
• evaluate LongCat-Flash against other leading LLMs
• deploy efficient LLM inference with high tokens-per-second throughput
• fine-tune or build on top of an open foundation model
• study MoE architecture with shortcut-connected design

When to choose

• you need a powerful open-weight MoE chat model with strong agentic capabilities
• you want cost-efficient inference with dynamic computation activation
• you need a non-thinking foundation model for building agents

When to avoid

• you lack GPU infrastructure for a 560B-parameter model
• you need a small model for edge or local laptop use
• you need a reasoning/thinking model rather than a foundation chat model

Facets

learning-resource · maturity active

llm-inference machine-learning deep-learning large-language-models artificial-intelligence python mixture-of-experts foundation-model open-weights huggingface meituan longcat-flash agentic-tasks model-weights ai-agents gpu linux docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="meituan-longcat/LongCat-Flash-Chat")