MMOOZZGG.com

Service

Run AI agents locally: an open model inside your perimeter

4 min read16 sources

To run AI agents locally, we put an open model inside your perimeter: on a computer in the office, on a server in your data center or on rented GPUs of a Russian provider. The agents are the same as on cloud models: sales, support, document review, client booking and a manager dashboard. Only the place where the model and the data live changes.

On this page · 6 sections

What we do

We choose an open model by your 50 requests: 8–9 billion, 30 billion or 70 billion parameters, Russian-language or global. We size the hardware with calculators and give a specification to buy or rent. We set up the engine for the load: one user or parallel work for a department. We build the agents behind one model interface, so the cloud and a local model switch by a setting. We set up routing for a hybrid design and anonymization before anything goes to the cloud. We add monitoring and hand everything to your engineer with instructions.

Pilot: 14 days, from $1,499

One agent on one process, on your own or rented hardware. The metric is in the contract: share of requests without an operator, minutes per document, response time. An exam on 50 requests before and after. The result: a working agent, a report with numbers and a hardware estimate for scaling. If the local model cannot handle the task, we say so in the report and show where the cloud can.

AI agent team: 4–6 weeks, from $4,999

3–5 agents on one local model with a shared knowledge base and task queue: for example, sorting incoming requests, answers from documents, draft preparation and a manager dashboard. A server or workstation to our specification, an engine for parallel work, and routing to the cloud for tasks on anonymized data. For large companies: from $18,000 in 2–3 months, with several departments and integrations.

Support: from $480 a month

Model and engine updates with a repeat exam, monitoring, incident reviews and a plan for a card failure. An AI director from $999 a month: a person who runs your agents and local infrastructure as a product, with a report to the top manager.

What we do not do

We do not sell hardware or take commissions from sellers: you buy to the specification wherever you like. We do not promise that a local model will do the job of a flagship model: the pilot tests this. We do not train models from scratch; fine-tuning on your data is possible as a separate project. We do not give legal opinions on 152-FZ and 243-FZ: we describe the architecture, and your lawyer gives the opinion.

Why we count both sides

We build agents on both cloud and local models, so we have no need to sell you a server. The calculators in this section show when the cloud is cheaper, and we say so in the pilot. Founder Mike Mozg runs a media channel and reviews cases in public; the numbers on this page are the same as in the contract.

Questions and answers

What hardware do you use for the pilot if we have none?

On a rented card in a Russian cloud: an RTX 4090 from about $0.50 an hour, an H100 from $3 an hour, and the rent is part of the pilot estimate. The data stays in Russia under the contract with the provider.

Can we move the agents to a cloud model later?

Yes, by a setting: the agents connect through one model interface. Moving from the cloud to a local model works the same way.

What happens to personal data in the pilot?

The pilot runs on anonymized or test data until the documents under 152-FZ, Russia’s personal data law, are signed. With a local model, the data does not leave your perimeter or a Russian cloud with a data processing agreement.

Sources and fact-checking

Checked by the editors on 29 September 2026.

  1. Tproger, cloud GPUs for ML in 2026, 21 May 2026 (tproger.ru)
  2. Intelion Cloud, H100/H200 rental (checked 29 September 2026) (intelion.cloud)
  3. Anti-Malware, 152-FZ and neural networks, 17 June 2026 (anti-malware.ru)
  4. GPU Index, RTX 4090 rental in Russia: 173 offers, from about $0.40 an hour (checked 30 September 2026) (gpuindex.ru)
  5. GPU Index, H100 rental in Russia: 41 offers, from $3 an hour (checked 30 September 2026) (gpuindex.ru)
  6. Digital Platforms, case No. 2447, October 2025: a large Russian bank (platforms.su)
  7. Digital Platforms, case No. 3855, 2 September 2026: the technology arm of a large Russian bank (platforms.su)
  8. Digital Platforms, case No. 4067, 2 September 2026: Alfa-Bank, IT executive (platforms.su)
  9. Digital Platforms, case No. 2929, 2025: a Russian IT holding (platforms.su)
  10. Digital Platforms, case No. 3475, 2 September 2026: NSIS, operator of the insurance information system (platforms.su)
  11. Digital Platforms, case No. 3661, 2 September 2026: Digital Sector and a client from IT infrastructure (platforms.su)
  12. Digital Platforms, case No. 4084, 2 September 2026: the cloud unit of a Russian internet group (platforms.su)
  13. Digital Platforms, case No. 2874, 2025: LANIT (platforms.su)
  14. Digital Platforms, case No. 3570, 2 September 2026: Ministry of Justice of Russia (platforms.su)
  15. Digital Platforms, case No. 3509, 2 September 2026: Moscow Health Department (platforms.su)
  16. Digital Platforms, case No. 3502, 2 September 2026: Pulkovo Airport (platforms.su)

Found a mistake? Tell us

Publications

Cases on this topic: 16

  • Market case · Russia

    A large Russian bank in-house LLMs solve 45% of requests; support costs estimated down at least 25% a year

    The bank put its own family of language models into its chatbot for LLM customer support: about 45% of customer requests are solved without an operator. In October 2025 it launched AI copilots for first-line operators, and more than 90% of support staff use them every day. The models run inside the bank’s network perimeter, so data does not leave the bank.

    Banks and finance

    source: platforms.su

    Read the case
  • Market case · Russia

    A large Russian financial group AI financial assistant on in-house language models, beta since 20 July 2026

    The group built an AI financial assistant for tasks linked to money and shopping, on its own family of large language models. To avoid made-up answers, the system relies on verified data sources, not only on what the model has learned. The beta was presented on 20 July 2026, and the full launch is planned for the autumn.

    Banks and finance

    2 September 2026 · source: platforms.su

    Read the case
  • Market case · Russia

    Alfa-Bank, IT head local agent on the Qwen 3.6–35B-A3B model: about 70 tokens per second on a Mac

    A local AI agent on Mac does autonomous work on a model with 35 billion parameters, about 3 billion of them active per token. It runs through LM Studio at about 70 tokens per second. The agent first ran in Docker on the Mac, then moved to a virtual machine, and the author calls that move a turning point for ease of use.

    Banks and finance

    2 September 2026 · source: platforms.su

    Read the case
  • Market case · Russia

    A large Russian IT holding contract approval in 3 days instead of two weeks, document comparison costs 40% lower

    The legal department of the holding, more than 70 lawyers, trained its own language model on the company’s legal data for over a year. Contract approval fell from two weeks to three days. AI contract comparison of two versions of a document is five times faster than by hand.

    IT companies

    source: platforms.su

    Read the case
  • Market case · Russia

    NSIS, insurance information system operator requests handled 20 times faster on a local LLM, 1.5 times more requests with no new hires

    The operator of the national insurance information system deployed a local LLM, a large language model on its own servers, and built three uses on it. The first is automatic processing of requests with many fields. The second is a RAG service for technical support that answers from company documents. The third is AI agents in software development, including automatic code review.

    IT companies

    2 September 2026 · source: platforms.su

    Read the case
  • Market case · Russia

    Digital Sector and an IT infrastructure client AI contract analysis agent in the client’s closed environment; in the integrator’s own testing, agents freed 20% of team time

    The integrator built an AI agent for first-pass contract analysis inside the closed network of a client that designs and supplies IT infrastructure. The agent extracts and matches data, finds discrepancies and prepares the result for a specialist. The integrator also put agents into its own testing process, which freed 20% of the team’s working time per sprint.

    IT companies

    2 September 2026 · source: platforms.su

    Read the case
  • Market case · Russia

    VK Tech two models fit into 22.4 GB of 24 GB of video memory with a 65,536-token context

    The team built a local AI agent in a closed environment with Ollama and an agent layer, on a rented GPU server with one NVIDIA A30 card of 24 GB. The models were gpt-oss 20b (13 GB) for text and tools and qwen3-vl 8b (6.1 GB) for images; with the KV cache for a 65,536-token context, they used 22.4 GB.

    IT companies

    2 September 2026 · source: platforms.su

    Read the case
  • Market case · Russia

    LANIT requirements gathering 4 times faster, document search time 66% lower on a local LLM platform

    The group built a platform that runs large language models on the customer’s own infrastructure: a chat and complex pipelines for documents, audio and images. A subsidiary built its own model, trained further on Russian-language data. It pilots the model in CRM, SRM and HRM projects and in corporate chatbots.

    IT companies

    source: platforms.su

    Read the case
  • Market case · Russia

    Ministry of Justice of Russia AI lawyer avatar with a base of federal laws; a local language model is being trained for it

    The country’s first AI lawyer avatar understands spoken language and advises on legal questions; its knowledge base holds federal laws, regulations and information from the ministry’s website. As of July 2026, specialists are training a local language model, which runs on the organization’s own servers, to speed up the work and improve the answers.

    Government

    2 September 2026 · source: platforms.su

    Read the case
  • Market case · Russia

    Moscow City Health Department AI assistant for hospital analytics on a local language model: data does not leave the network

    An AI assistant built on a locally deployed large language model sits inside the data marts of the city’s unified medical system. Local deployment was chosen to work with sensitive medical data without sending it outside.

    Government

    2 September 2026 · source: platforms.su

    Read the case
  • Market case · Russia

    Pulkovo Airport AI secure code review plugin in a closed network: over 90% accuracy on checking findings and up to 85% on fixes

    The airport’s information security team built code analysis into the development environment. A trained AI plugin reviews vulnerabilities and fixes the code inside a closed network, so no data goes outside. The model verifies findings with more than 90% accuracy and fixes vulnerabilities with up to 85% accuracy.

    Industry and infrastructure

    2 September 2026 · source: platforms.su

    Read the case
  • Market case · Russia

    Step agroholding its own AI ecosystem on local neural networks, so data never goes to public services

    The holding builds its AI ecosystem on local AI models for companies, agents and chatbots, so confidential data does not go to public services. It already syncs herd management data with a government system and runs legal information monitoring for the back office. Several analytics projects have started.

    Industry and infrastructure

    2 September 2026 · source: platforms.su

    Read the case
  • Market case · Russia

    Developer MR Project finance AI controller in an isolated environment: 80% less time on credit document analysis

    The developer and its bank built a project finance AI controller on a Russian language model. It checks the terms of project finance automatically and tracks loan obligations. According to the company, the time spent on credit document analysis fell by 80%. Each large project comes with hundreds of pages of credit documents and dozens of additional agreements; the system assembles a master version of each contract and keeps one calendar of obligations.

    Industry and infrastructure

    15 September 2026 · source: comnews.ru

    Read the case
  • Market case · Russia

    Faberlik neural catalog search on a local Qwen model and rented GPUs

    The cosmetics maker replaced classic catalog search with neural search: a local Qwen language model and vector semantic search run on the GPU infrastructure of a Russian cloud. The model works inside infrastructure the company controls, data is not sent to outside services, and the cost of handling requests stays under control.

    Retail and manufacturing

    2 September 2026 · source: platforms.su

    Read the case
  • Market case · Russia

    Petrovich-Tech a local model with 9 billion parameters matched cloud models on tasks of 2–3 steps: 27 runs

    The IT unit of a building materials store chain compared three models in one agent setup with 13 analytics dashboard widgets and about 30 tools: a Western cloud model, an open cloud model with 235 billion parameters and a local model with 9 billion parameters in 4-bit quantization on one graphics card. The design: 3 scenarios, 3 models, 3 runs, 27 launches.

    Retail and manufacturing

    2 September 2026 · source: platforms.su

    Read the case
  • Market case · Russia

    T2 (Tele2) tender for a self-hosted AI coding assistant in a closed data center: 15 developers, response within 400 ms

    In February 2026 the operator announced a tender for a self-hosted AI coding assistant that runs in the company’s closed data center in Rostov-on-Don, so source code never leaves its infrastructure. Requirements: 15 users, autocomplete with a response of at most 400 ms, six programming languages.

    Telecom

    2026 · source: platforms.su

    Read the case
Contact us