TextVoice assistantsText to speech

LongCat

Models from Meituan, China's largest delivery service. LongCat-Flash adjusts compute to query complexity; LongCat-2.0 has 1.6 trillion parameters under MIT. Omni models (Flash-Omni, Next) and AudioDiT speech synthesis too.

Developer
Meituan, China
First release
Aug 2025
Latest release
Jul 2026
Sizes
1B – 1.6T-A48B
License
Commercial use allowedMIT
Russian
Not stated
Ready-made builds
GGUF, MLX (Apple)
Running
On your own serverNeeds a GPU
Industries
Retail and marketplaces, Customer support, Manufacturing and logistics
Deploy on your server Hugging Face GitHub

What it does

  • Agents for orders and service processes
  • Corporate assistant
  • Analysis of long documents

Where it is used

Retail and deliveryCustomer supportLogistics

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. LongCat-2.0
  2. LongCat-Next 74B-A3B / AudioDiT (1B, 3.5B)
  3. LongCat-Flash-Lite
  4. LongCat-Flash-Omni 560B-A27B
  5. LongCat-Flash-Thinking
  6. LongCat-Flash-Chat

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can LongCat be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does LongCat need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does LongCat support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download LongCat and what does it cost?

The LongCat weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

TextDeepSeekDeepSeek · ChinaCommercial use allowed

DeepSeek's flagship line: from the first 7B/67B to V4-Pro with 1.6 trillion parameters. Closed-model quality under an open MIT license; V4-Flash-Vision-Exp and V4.1-Flash understand images, context up to 1M tokens.

DetailsTextLing / RingAnt Group (inclusionAI) · ChinaCommercial use allowed

An Ant Group family: Ling for standard models, Ring for reasoning ones. There are trillion-parameter flagships and the efficient Ling-3.0-tiny, which needs only 1.3 billion active parameters.

DetailsTextMiMoXiaomi · ChinaCommercial use allowed

Xiaomi models for reasoning and agents: from the compact MiMo-7B to MiMo-V2.6-Pro with 1.02 trillion parameters. The larger versions understand text, images, video and audio, with a 1M token context. Languages: English and Chinese.

Details

Source: huggingface.co/meituan-longcat/LongCat-2.0. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.