MMOOZZGG.com

Comparison

Ollama vs LM Studio vs llama.cpp vs vLLM: which engine should run your local model?

3 min read10 sources

In Ollama vs LM Studio, choose LM Studio when a person uses the model and Ollama when a program does. A model is a file, and an engine runs it. The engine decides the speed, how many people can use the model at once and whether your agent can connect to it like a cloud service. Below is a comparison of Ollama, LM Studio, llama.cpp and vLLM: who each engine is for and how it fits the hardware in this section.

On this page · 5 sections

LM Studio: one person, a Mac or a laptop

A desktop app: pick a model from the catalog, press download, start a chat. It shows speed in tokens per second after every answer and starts a local API compatible with common libraries. It fits testing models before you buy hardware and running a personal agent. This is how the personal agent of a bank’s IT executive works on a Mac.

Ollama: one or two people, a developer team

A command-line tool and a background service: one command installs a model, another starts the API. It fits integrations and scripts better than LM Studio, runs on Mac, Linux and Windows, and works on graphics cards and Apple Silicon. The limit is the same: single requests are fast, but with many at once, some wait in a queue.

llama.cpp: the base and the benchmarks

The library on which LM Studio, Ollama and dozens of other programs are built. Its benchmark table for Apple Silicon is the source of the figures in this section: M4 Max 83.1 tokens per second and M5 Max 119.9 on the Llama 2 7B model in 4 bits. Use it directly when you need full control over parameters and minimal overhead.

vLLM: a server for a department

A batch serving engine for graphics cards: it handles dozens of requests at once, sharing cache memory between them, and by our estimate gives a total speed of thousands of tokens per second on a server card. By our estimate, it turns a server with two 96 GB cards into a service for 10–20 users, and four H100s into a service for hundreds. It is built for Linux servers with graphics cards and needs an engineer.

How to choose

One user on a Mac or a laptop: LM Studio. A developer or an integration on one computer: Ollama. A department and agents with a request queue on a server with graphics cards: vLLM. Our agents connect to any of them through one model interface, so moving from the cloud to a local engine and back is a setting, not a rewrite.

Questions and answers

Do you need Linux for a local model?

Not for one user: LM Studio and Ollama run on macOS and Windows. For a server with vLLM, yes.

Can you run vLLM on a Mac Studio?

Not for a department: vLLM is built for servers with graphics cards. On a Mac, several users are served with llama.cpp in server mode with parallel slots, and the speed per stream drops.

Sources and fact-checking

Checked by the editors on 29 September 2026.

  1. llama.cpp, performance on Apple Silicon, table updated 25 August 2026 (github.com)
  2. GPU-Benchmarks-on-LLM-Inference, Llama 3 8B and 70B, May 2024 (github.com)
  3. Digital Platforms (Tsifrovye Platformy), case No. 2447, October 2025: a large Russian bank (platforms.su)
  4. Digital Platforms (Tsifrovye Platformy), case No. 3855, 2 September 2026: the technology arm of a large Russian bank (platforms.su)
  5. Digital Platforms (Tsifrovye Platformy), case No. 4067, 2 September 2026: Alfa-Bank, IT executive (platforms.su)
  6. Digital Platforms (Tsifrovye Platformy), case No. 2929, 2025: a Russian IT holding (platforms.su)
  7. Digital Platforms (Tsifrovye Platformy), case No. 3475, 2 September 2026: NSIS, operator of the insurance information system (platforms.su)
  8. Digital Platforms (Tsifrovye Platformy), case No. 3661, 2 September 2026: Digital Sector and a customer from IT infrastructure (platforms.su)
  9. Digital Platforms (Tsifrovye Platformy), case No. 4084, 2 September 2026: the enterprise cloud unit of a large Russian internet company (platforms.su)
  10. Digital Platforms (Tsifrovye Platformy), case No. 2874, 2025: LANIT (platforms.su)

Found a mistake? Tell us

Publications

Mike Mozg

Agentic AI use cases at AT&T: nearly 500 processes now run on agents

AT&T no longer uses AI only to help staff work faster: it is rebuilding whole business processes around agents. SiliconANGLE reported on 14 November 2026 that nearly 500 agentic AI use cases at AT&T are already in production. Here is how the company rebuilds them, where a human still checks the agent, and what other large companies can take from it.

News4 min

Cases on this topic: 8

  • 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
Contact us