MMOOZZGG.com

Comparison

Open source vs proprietary AI models: where each wins

5 min read17 sources

In open source vs proprietary AI models, an open model on your own hardware costs less per token at volume and keeps data at home, while the cloud model in the test more often handled long chains of steps. Below, open and closed models are compared by task, with numbers from cases and measurements, not general words.

On this page · 5 sections

Where an open model is just as good

Short chains of actions: in 27 runs by the IT unit of a store chain, a local model with 9 billion parameters was as good as cloud models on chains of 2–3 steps. Extracting fields from documents, sorting requests, answers from a knowledge base with search, email drafts: in our estimate, models of 8–32 billion parameters handle these; test on your own data. Russian language: the open 32B model of a large Russian bank and the open 8B model of a large Russian technology company are built for Russian. Tasks with a fixed answer format where the model was fine-tuned on your own data: the legal department of an IT holding trained a model on its own contracts for more than a year and cut contract approval from two weeks to three days.

Where it loses

Long chains: on 15 steps, no model gave a fully verifiable result, but a large 235-billion cloud model gave partial success in 2 runs of 3, and the 9-billion local model in 1 of 3, with 2 false reports of completion. Complex code and architecture decisions, legal analysis of long contracts, reasoning with dozens of conditions: for these, people pay $51 per million output tokens for Fable 5.1 and GPT-6 Astra. A vision model and speech at the same time: locally this means two models and memory for both. Speed on a long context on one computer: in a 2025 measurement, a 671-billion model on a Mac Studio M3 Ultra with 512 GB reads 8,000 tokens in almost 15 minutes.

Price per token

At 60 million tokens a month, cloud models cost from $12 on GPT-6 Luna to $1,200 on flagships, and $900 on a large Russian cloud model. An open model on a workstation with an RTX 5090 costs about $800 a month including an engineer, at any volume up to the card’s limit: $5 per million tokens on an 8-billion model in one stream at 50% load. A 70-billion model does not fit on one card; on a workstation with two RTX 5090 cards at about $1,100 a month, it costs $46 per million. The open model wins on money at volume with mid-size models and loses at low volume and against cheap cloud models.

Data and the law

An open model on your own hardware: data does not leave the perimeter, you need no processing contract with the model vendor, and the architecture ensures data localization, while your other duties as an operator under 152-FZ, Russia’s personal data law, remain. Foreign flagships: Russian addresses are not in their supported regions, payment goes through intermediaries, and most of them have no processing contract. Russian clouds: a contract with a Russian legal entity and data in Russia, but the setup belongs to someone else. Under 243-FZ, the developer of both a sovereign and a national model is a Russian legal entity, and answers and data are processed in data centers in Russia owned by Russian legal entities; a national model may include components under an open license, including other people’s open models. The status goes to the model and its developer, not to the company that runs the model on its own hardware; these rules come into force on 1 March 2027.

How to choose

Split the task into steps and count how long the chain is: on chains of up to 3 steps, the open model in the test was as good as cloud models; for long chains, test the cloud or a hybrid. Take 50 of your own requests and run them on three models: an open 8–9 billion model, an open 30–70 billion model and a mid-range cloud model. Count not the price per token but the price of a solved task: a model that is wrong in 10% of cases costs as much as a person’s time to fix those 10%.

Questions and answers

Which open model should you take for the Russian language?

An open 32B model from a large Russian bank, an open 8B model from a large Russian technology company, and foreign open models with good Russian that we test in a pilot. Choose by 50 of your own requests, not by rankings.

Can you fine-tune an open model on your own data?

Yes, and this is the main advantage: an IT holding trained a model on its own contracts for more than a year and got contract approval in 3 days instead of two weeks. Fine-tuning is a separate project with data, labeling and weeks of GPU time; for most tasks, search over documents without fine-tuning is enough.

Sources and fact-checking

Checked by the editors on 29 September 2026.

  1. GPU-Benchmarks-on-LLM-Inference, Llama 3 8B and 70B, May 2024 (github.com)
  2. Hardware Corner, DeepSeek 671B on Mac Studio M3 Ultra 512 GB, 27 March 2025 (hardware-corner.net)
  3. Claude Platform, API prices (checked 29 September 2026) (platform.claude.com)
  4. Puter, overview of OpenAI API prices based on openai.com, 29 September 2026 (developer.puter.com)
  5. kalinkindev.ru, API prices of a large Russian cloud model from its cloud billing, 13 September 2026 (kalinkindev.ru)
  6. iXBT, a large Russian bank released an open 32B model under Apache 2.0, 18 July 2025 (ixbt.com)
  7. A large Russian technology company, open weights of an 8B model, 25 February 2025 (yandex.ru)
  8. CNews, which AI models will get sovereign status, 28 September 2026, material marked as advertising (corp.cnews.ru)
  9. Claude Platform, supported regions (checked 29 September 2026) (platform.claude.com)
  10. OpenAI, supported countries for the API (checked 29 September 2026) (developers.openai.com)
  11. Digital Platforms, case no. 4027, 2 September 2026: Faberlic (platforms.su)
  12. Digital Platforms, case no. 4085, 2 September 2026: Petrovich-Tech (platforms.su)
  13. Digital Platforms, case no. 2447, October 2025: a large Russian bank (platforms.su)
  14. Digital Platforms, case no. 3855, 2 September 2026: the technology group of a large Russian bank (platforms.su)
  15. Digital Platforms, case no. 4067, 2 September 2026: Alfa-Bank, IT manager (platforms.su)
  16. Regard, GeForce RTX 5090: one card on sale, 30 September 2026 (regard.ru)
  17. Federal Law No. 243-FZ of 26 July 2026, text on ConsultantPlus (consultant.ru)

Found a mistake? Tell us

Publications

Cases on this topic: 5

  • 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

    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
Contact us