Math and reasoningCode

Kimina-Prover

Models for formal proofs in Lean 4 from Moonshot AI (Kimi) and Numina. Small versions from 0.6B run on a laptop.

Developer
Moonshot AI and Project Numina, China, France
First release
Apr 2025
Latest release
Aug 2025
Sizes
0.6B – 72B
License
Commercial use allowedKimina-Prover-72B: MIT; the rest: Apache 2.0
Russian
Not supported
Ready-made builds
GGUF
Running
On your own serverAlso runs without a GPU
Industries
Science and research, Education, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Formal verification of mathematical workings
  • Translating a problem from plain language into Lean
  • Training and olympiad preparation

Where it is used

Research groupsEducationSafety-critical software development

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
no versions

Versions

  1. Kimina-Prover-RL 0.6B и 1.7B
  2. Kimina-Prover-72B и Distill 1.7B, 8B
  3. Kimina-Prover-Preview-Distill и Autoformalizer

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 Kimina-Prover be used in a commercial project?

Yes. License: Kimina-Prover-72B: MIT; the rest: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Kimina-Prover need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Kimina-Prover support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Kimina-Prover and what does it cost?

The Kimina-Prover 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

Math and reasoningDeepSeek-ProverDeepSeek · ChinaCommercial use with conditions

DeepSeek models for formal proofs in Lean 4: the proof is checked by a program, not a person. A narrow tool for mathematicians and engineers.

DetailsMath and reasoningGoedel-ProverPrinceton University · USACommercial use allowed

Open models for formal proofs in Lean 4 from Princeton. The new Goedel-Code-Prover proves program correctness.

DetailsTextKimiMoonshot AI · ChinaCommercial use with conditions

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.

Details

Source: huggingface.co/api/models?author=AI-MO&sort=createdAt&direction=-1. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.