// local-llm · ollama/ollama

Ollama

Ollama is an open-source local llm project by ollama (ollama/ollama on GitHub). It has 182,098 GitHub stars and 18,090 forks, is released under the MIT license, and was last updated on GitHub on 3 October 2026.

The simplest way to run open language models on your own machine.

★ 182.1k stars⑂ 18.1k forksMITupdated 2026-10

View on GitHub ↗Official site & model library ↗

▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.

// project facts

Project facts

Repository: ollama/ollama
GitHub stars: 182,098
Forks: 18,090
License: MIT
Last updated on GitHub: 3 October 2026
Category: Local LLM
Listing: Full install guide
Official site: Official site & model library

// how it works

How it works

Install with one command
macOS and Linux use the install script; Windows uses a one-line PowerShell command. Desktop downloads exist too.
Run a model
Type ollama run followed by a model name — your first run downloads the weights, then you are chatting.
Connect your tools
Point coding agents, chat apps, and your own code at Ollama's local API instead of a cloud endpoint.
Expand the library
Pull new models anytime with ollama pull and switch between them freely.

// features

Why people love it

One-command install

macOS, Windows, Linux, and Docker — up and running in about a minute.

Huge model library

Llama, Qwen, Gemma, DeepSeek, gpt-oss, Kimi, GLM, MiniMax, Mistral, and more, in multiple sizes.

Local API

An OpenAI-style local endpoint your apps and agents can call with zero cloud dependency.

Agent integrations

Works with Claude Code, Codex, Copilot CLI, OpenCode, OpenClaw, and other harnesses.

Assistant mode

Turn it into a personal assistant across WhatsApp, Telegram, Slack, and Discord.

Client libraries

First-party Python and JavaScript libraries plus a big community ecosystem.

// run it

Run it yourself

Step 1 — Install

macOS / Linux: run the install script. Windows: run the PowerShell one-liner.

curl -fsSL https://ollama.com/install.sh | sh
# Windows PowerShell:
irm https://ollama.com/install.ps1 | iex

Step 2 — Run a model
Start chatting with any model from the library.
```
ollama run gemma4
```
Step 3 — Build on it
Call the local API from your app, or launch an integration such as a coding agent.
```
ollama launch claude
```

// use cases

What you can build

A private AI assistant that works offline.
Coding help inside your editor via agent integrations.
Prototyping AI features without API keys or bills.
Learning how LLMs behave, hands-on and locally.

Local models also power the security shelf: Pentest Harness bills itself as a heaven for hackers — a penetration-testing harness built to run on local models rather than cloud APIs. Also on this shelf: entroly — Cut AI context cost with reversible, byte-exact compression. Readers working through the Local LLM shelf also stop at kotaemon, an open-source RAG-based tool for chatting with your documents.

// faq

Questions, answered

Is Ollama free?

Yes — MIT licensed, free for personal and commercial use, with no account required.

Do I need a GPU?

No — it runs on CPU too, though a GPU makes larger models much faster. Smaller models fly even on modest machines.

Ollama or Unsloth?

Ollama is the easiest way to run models. Unsloth adds training and fine-tuning. Many people use Ollama to run what Unsloth helped them train.

Which model should I start with?

The library lists sizes and strengths per model — start small (a few GB) and scale up if your machine handles it.

Can apps use it?

Yes — the local API plus official Python/JS libraries make it a popular backend for indie AI apps.

// keep exploring

Similar tools

Local LLM

Unsloth

Run and fine-tune LLMs and diffusion models locally — faster training, smaller memory footprint.

★ 77.2k starsApache-2.0

View guide →

Easy Install

Pinokio

A one-click browser for open-source AI apps — discover, install, and run anything.

★ 8.2k starsMIT

View guide →

Audio

Qwen3-TTS

Alibaba's open voice models: expressive, streaming-capable speech with free-form voice design.

★ 13.6k starsApache-2.0

View guide →

Local LLM

atomic-agent

Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.

★ 2.7k starsMIT

View guide →

Local LLM

node-llama-cpp

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

★ 2.2k starsMIT

View guide →

Local LLM

BitNet

BitNet — Microsoft's official inference framework for 1-bit large language models, running fast on ordinary CPUs, MIT

★ 41.2k starsMIT

View guide →

// alternatives

Alternatives in Local LLM

The most-starred other Local LLM projects in the LibreAI catalogue — the realistic shortlist if Ollama is not the right fit.

Open Webui★ 153.9k
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
llama.cpp★ 130.2k
LLM inference in C/C++
vLLM★ 93.1k
A high-throughput and memory-efficient inference and serving engine for LLMs
lobehub★ 83.0k
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
GPT4All★ 77.4k
GPT4All — run local LLMs on any device: a free desktop chat client and Python SDK that run open models entirely on your CPU, no GPU or cloud required

// more in local-llm

Get Ollama

Free and open — grab the source, star the repo, and start creating.

View on GitHub ↗← More Local LLM tools

Ollama

Project facts

How it works

Why people love it

One-command install

Huge model library

Local API

Agent integrations

Assistant mode

Client libraries

Run it yourself

What you can build

Questions, answered

Similar tools

Unsloth

Pinokio

Qwen3-TTS

atomic-agent

node-llama-cpp

BitNet

Alternatives in Local LLM

More in Local LLM

Get Ollama