0
Local LLM runnersMITGo

Ollama

Get up and running with large language models locally.

GitHubWebsite
Stars
183.2K
Forks
18.3K
Open issues
4.3K
Last commit
2026-10-15

Live from the GitHub API · updated 2026-10-15

What is Ollama?

Ollama downloads and runs open models such as Llama, Qwen, Gemma, Mistral and DeepSeek with one command and exposes a local REST API that many apps integrate with. It handles quantized model files, GPU offloading and model customization through Modelfiles.

Key features

  • One-command model download and chat
  • Local REST API (OpenAI-compatible endpoint)
  • Modelfiles for custom system prompts and parameters
  • Vision and embedding models

System requirements

Platforms
Windows · macOS · Linux · Docker
GPU
Optional; NVIDIA, AMD and Apple Silicon accelerated
RAM
8 GB for 7B models, 16 GB for 13B, 32 GB+ for larger

How to install Ollama

Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.

macOS / Windows

  1. 1
    Download and run the installer from ollama.com.
  2. 2
    Run a model.
    ollama run llama3.2

Linux

  1. 1
    Install with the official script.
    curl -fsSL https://ollama.com/install.sh | sh
  2. 2
    Run a model.
    ollama run llama3.2

Docker

  1. 1
    Start the server (add --gpus=all for NVIDIA).
    docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
docker exec -it ollama ollama run llama3.2

Strengths

  • Easiest way to run local LLMs
  • Huge app ecosystem

Limitations

  • Less control than raw llama.cpp

Ollama alternatives compared

SoftwareStarsLicensePlatformsVRAM
Ollama

Get up and running with large language models locally.

183.2KMIT—
llama.cpp

LLM inference in C/C++ — the engine behind most local AI apps.

131.2KMIT—
Jan

Open-source ChatGPT-style desktop app that runs 100% offline.

45KAGPL-3.0—
LocalAI

Self-hosted, OpenAI-compatible API for text, images, audio and more.

49.5KMIT—
GPT4All

Private, on-device chat with local document Q&A.

77.4KMIT—
vLLM

High-throughput LLM serving engine with PagedAttention.

93.8KApache-2.0—

FAQ

Is Ollama free?

Yes — Ollama is open-source software released under the MIT license. Check the license (and any model weight licenses) before commercial use.

Does Ollama run on Windows, Mac and Linux?

Ollama supports: Windows, macOS, Linux, Docker.

What hardware do I need for Ollama?

Optional; NVIDIA, AMD and Apple Silicon accelerated. RAM: 8 GB for 7B models, 16 GB for 13B, 32 GB+ for larger

How do I install Ollama?

1. Download and run the installer from ollama.com. 2. Run a model.

What are the best Ollama alternatives?

Popular alternatives include llama.cpp, Jan, LocalAI, GPT4All. See the comparison table on this page.

Tools to run LLMs locally