LongCat-Flash
LongCat-Flash is an open-weights language model from Meituan Inc, released September 1, 2025. It has 562B parameters (dense). The context window is 128K tokens.
We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and advanced agentic capabilities.
Check it against your own PC →
Can you run LongCat-Flash locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Too large | – | – | – | – |
Ready-made quantizations on Hugging Face: ggml-org/LongCat-Flash-Chat-GGUF · mlx-community/LongCat-Flash-Chat-4bit · finding1/LongCat-Flash-Chat-MLX-5.5bpw
Benchmark results
Epoch AI has not published results for LongCat-Flash yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: meituan-longcat/LongCat-Flash-Chat