LongCat-2.0 - 1.6T MoE trained entirely on AI ASICs

Ran it through some tricky math problems and the responses came back noticeably quick for a model this size. Curious to see how the open weights hold up on longer agentic workflows.

Finally got around to testing LongCat-Flash-Thinking on some multi-step coding problems and the speed honestly caught me off guard, especially for a 560B MoE. The reasoning chains feel surprisingly tight too.

Pulled LongCat-Flash-Thinking for some debugging yesterday and the response time genuinely caught me off guard. Reasoning feels sharp without the usual lag.

finally a chinese-built model that actually feels fast on long reasoning chains. really impressed how it handled a math-heavy prompt without losing the thread halfway through.

Curious how this stacks up against DeepSeek or Qwen on coding benchmarks, and is the 560B MoE actually deployable on a single node or do you need serious infra to run it locally?

LongCat handled a tricky multi-step coding prompt way faster than I expected, and the reasoning chain felt genuinely clear instead of just confident. The MoE setup seems to pay off in practice.

Tried it on a logic puzzle and the reasoning came back structured and fast, way smoother than I expected for a 560B model.

Ran a coding question through LongCat-Flash-Thinking and the response came back fast with clean, working code instead of long-winded explanations. Really impressed by how snappy it feels for such a big model.

How does the 560B MoE setup compare on inference cost versus a dense model of similar capability, and is there any self-hosting guidance for teams without massive GPU budgets?

how does the 560B MoE setup handle latency on longer reasoning chains, and is there a hosted endpoint or is it self-host only?