TextImage + textCode

Kimi

Very large Moonshot MoE models for agentic work. K3 (2.8 trillion parameters) was the largest open model at release, with up to 1M tokens of context and image understanding; K2.7-Code is built for programming.

Developer
Moonshot AI, China
First release
Feb 2025
Latest release
Jul 2026
Sizes
16B-A3B – 2.8T-A104B
License
Commercial use with conditionsK2–K2.7-Code: modified MIT (at 100 million users or $20 million monthly revenue, Kimi must be credited in the interface); K3: own Kimi K3 License, API businesses with revenue from $20 million a year need a separate agreement
Russian
Not stated
Ready-made builds
GGUF, AWQ, MLX (Apple)
Running
On your own serverNeeds a GPU
Industries
Software development, Science and research, Finance
Deploy on your server Hugging Face GitHub

What it does

  • Multi-step agents: search, data collection, reports
  • In-depth document analysis
  • Help for developers
  • Analysis of screenshots and spreadsheets

Where it is used

Analytics departmentsSoftware developmentConsultingMarket research

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. Kimi K3
  2. Kimi K2.7-Code 1T-A32B
  3. Kimi K2.6
  4. Kimi K2.5
  5. Kimi K2 Thinking
  6. Kimi Linear 48B-A3B
  7. Kimi K2
  8. Moonlight 16B-A3B

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 Kimi be used in a commercial project?

With conditions. License: K2–K2.7-Code: modified MIT (at 100 million users or $20 million monthly revenue, Kimi must be credited in the interface); K3: own Kimi K3 License, API businesses with revenue from $20 million a year need a separate agreement. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Kimi need?

At minimum: One GPU with 16–80 GB — mid-size 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 Kimi 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 Kimi and what does it cost?

The Kimi 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.

Comparisons

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.

DetailsTextGLM (ChatGLM)Zhipu AI (Z.ai) · ChinaCommercial use with conditions

One of the oldest Chinese open lines: from ChatGLM-6B to GLM-5.3. Strong at agentic tasks and programming; GLM-5.3-Flash understands images and is released under MIT.

DetailsImage + textKimi-VLMoonshot AI · ChinaCommercial use allowed

An efficient MoE vision model (16B, 3B active) with a long context and a reasoning version. Handles long documents and video well.

Details

Source: huggingface.co/moonshotai/Kimi-K3. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.