TextImage + text

DeepSeek

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.

Developer
DeepSeek, China
First release
Nov 2023
Latest release
Sep 2026
Sizes
7B – 1.6T-A49B
License
Commercial use allowedMIT (V2 and earlier versions: DeepSeek's own license prohibiting harmful use)
Russian
Not stated
Ready-made builds
GGUF, AWQ, GPTQ, MLX (Apple)
Running
Available in OllamaNeeds a GPU
Industries
Legal, Finance, Customer support, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Employee assistant on your own server
  • Analysis of long contracts and reports
  • Agents that work with tools and APIs
  • Help for developers

Where it is used

Legal and financeCustomer supportIT departmentAnalytics

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-V4.1-Flash
  2. DeepSeek-V4-Pro-0813 / V4-Flash-Vision-Exp
  3. DeepSeek-V4-Flash-0731
  4. DeepSeek-V4-Pro / V4-Flash
  5. DeepSeek-V3.2
  6. DeepSeek-V3.1
  7. DeepSeek-V3
  8. DeepSeek-V2.5
  9. DeepSeek-V2
  10. DeepSeek-MoE 16B
  11. DeepSeek LLM 7B / 67B

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
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 be used in a commercial project?

Yes. License: MIT (V2 and earlier versions: DeepSeek's own license prohibiting harmful use). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does DeepSeek 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 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 and what does it cost?

The DeepSeek 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

TextDeepSeek-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.

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.

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.

Details

Source: huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.