LLM Models

We introduce an updated version of LongCat-Flash-Thinking-2601, a powerful and efficient Large Reasoning Model (LRM) with 560 billion total parameters, built upon an innovative Mixture-of-Experts (MoE) architecture. Beyond inheriting the domain-parallel training recipe in our pre…

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

Model Introduction We introduce LongCat-Flash-Omni , a state-of-the-art open-source omni-modal model with 560 billion parameters (with 27B activated), excelling at real-time audio-visual interaction, which is attained by leveraging LongCat-Flash's high-performance Shortcut-connec…

We introduce and release LongCat-Flash-Thinking , which is a powerful and efficient large reasoning model (LRM) with 560 billion total parameters, featuring an innovative Mixture-of-Experts (MoE) architecture. The model incorporates a dynamic computation mechanism that activates…

🤗 Hugging Face 💻 Github Repository 📑 Technique Report 💬 Issues & Discussions

🤗 Hugging Face 💻 Github Repository 📑 Technique Report 💬 Issues & Discussions

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...