Math and reasoningText

DeepSeek-Math

DeepSeek's maths models. The first 7B version introduced the GRPO training method; the 685B V2 writes and checks its own olympiad-level proofs.

Developer
DeepSeek, China
First release
Feb 2024
Latest release
Nov 2025
Sizes
7B – 685B
License
Commercial use with conditionsDeepSeekMath 7B: DeepSeek's own license (commercial use allowed with restrictions); DeepSeek-Math-V2: Apache 2.0
Russian
Not stated
Ready-made builds
GGUF
Running
On your own serverNeeds a GPU
Industries
Science and research, Finance, Education
Deploy on your server Hugging Face GitHub

What it does

  • Calculations and formula checks
  • Checking mathematical workings in reports
  • Working through problems step by step
  • Training

Where it is used

Finance and analyticsEngineering companiesEducation

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. DeepSeek-Math-V2
  2. DeepSeekMath 7B

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 DeepSeek-Math be used in a commercial project?

With conditions. License: DeepSeekMath 7B: DeepSeek's own license (commercial use allowed with restrictions); DeepSeek-Math-V2: Apache 2.0. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does DeepSeek-Math 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-Math 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-Math and what does it cost?

The DeepSeek-Math 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 reasoningQwen2.5-MathQwen (Alibaba) · ChinaCommercial use with conditions

Maths versions of Qwen: they solve problems step by step and can calculate via code. Includes reward models that check each step of a solution.

DetailsTextDeepSeek-R1DeepSeek · ChinaCommercial use allowed

A reasoning model that thinks step by step before answering. Strong at calculations, logic and code; compact distilled versions are available.

Details

Source: huggingface.co/deepseek-ai/DeepSeek-Math-V2. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.