DeepSeek-Prover
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.
- Developer
- DeepSeek, China
- First release
- Aug 2024
- Latest release
- Apr 2025
- Sizes
- 7B – 671B
- License
- Commercial use with conditionsDeepSeek's own license (commercial use allowed with restrictions)
- Russian
- Not stated
- Ready-made builds
- GGUF
- Running
- On your own serverNeeds a GPU
- Industries
- Science and research, Software development, Education
What it does
- Formal verification of mathematical workings
- Verifying algorithm correctness
- Training and olympiad preparation
Where it is used
Hardware requirements
Versions
- DeepSeek-Prover-V2 7B и 671B
- DeepSeek-Prover-V1.5
- DeepSeek-Prover-V1
How to run it
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 DeepSeek-Prover be used in a commercial project?
With conditions. License: DeepSeek's own license (commercial use allowed with restrictions). Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.
What hardware does DeepSeek-Prover 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 DeepSeek-Prover 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 DeepSeek-Prover and what does it cost?
The DeepSeek-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
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
Models for formal proofs in Lean 4 from Moonshot AI (Kimi) and Numina. Small versions from 0.6B run on a laptop.
DetailsMath and reasoningGoedel-ProverPrinceton University · USACommercial use allowedOpen models for formal proofs in Lean 4 from Princeton. The new Goedel-Code-Prover proves program correctness.
DetailsMath and reasoningDeepSeek-MathDeepSeek · ChinaCommercial use with conditionsDeepSeek's maths models. The first 7B version introduced the GRPO training method; the 685B V2 writes and checks its own olympiad-level proofs.
DetailsSource: huggingface.co/deepseek-ai/DeepSeek-Prover-V2-7B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


