Translated with AI from the Russian original.

The MWS AI team has opened access to a large language model for writing computer code. The assistant is based on a language model with 1.5 billion parameters, which can be run even on a laptop to test basic use cases without additional investment.

Kodify Nano is available for download on theMWS AI website and theHugging Face platform, and also comes with a plugin compatible with popular editors and development environments. It can be deployed in a closed loop, which eliminates the risk of code leakage, adapted to specific tasks, and fine-tuned on your own data. The quantized version of the model requires only 1 GB of RAM.

Key features of Kodify Nano:

  • supports a context of up to 32,000 tokens (approximately 16-25,000 lines of code, depending on the language);
  • recognizes 90 programming languages, including Python, Java, JavaScript, C#, and Go;
  • can automatically complete and improve code, write tests, create documentation, generate code from a description, and explain someone else's code.

The model is based on Qwen2.5-Coder, and MWS AI used its own dataset with a large amount of code in different languages to fine-tune it.

Kodify Nano is the company's second open model. In November 2024, MWS AI released Cotype Nano, a language model for content creation, data analysis, and customer support. In six months, it has been downloaded more than 10,000 times.

Now on the front page

Articles

Why even a PC case should be branded

In Russian conditions, the popularity of PCs assembled by small local companies or in-house corporate IT departments continues to grow rapidly. Such solutions have historically been more popular in Russia than in other developed markets, but today new nuances have emerged in the segment's evolution, which we discussed with Karim LASKRI, Business Director of FSP Group in the CIS region.

News

Storage you can trust in the background: Basis SDS 2.3 released with scheduled diagnostics and an observer role

A storage system is the only infrastructure layer where an error cannot be “rolled back”: neither a reboot nor a configuration rollback will restore lost data. That is why users expect predictability from software-defined storage rather than just new features—ensuring background processes finish what they started, and administrators can see the cluster status not only “right now,” but also over time.