Ollama

The easiest way to run large language models locally

5.0•34 reviews•

418 followers

The easiest way to run large language models locally

5.0•34 reviews•

418 followers

Visit website

AI Infrastructure Tools

Run Llama 2 and other models on macOS, with Windows and Linux coming soon. Customize and create your own.

Free

Launch tags:

Artificial Intelligence•GitHub

Launch Team

Jeff Morgan

Ollama

Maker

📌

Hi Product Hunt! I'm one of the makers and maintainers of Ollama, an open-source tool that makes it easy to get up and running with local large language models (LLMs) like Meta's Llama 2. Local LLMs are a bunch of fun! They're private, free to use and most excitingly there's a growing number of fine-tuned models available to run for different use cases. We're working hard to make Ollama easier to use in your workflow. LangChain recently added an Ollama integration, and we've designed Ollama with an easy to use API, making it easy to integrate into an existing app or build entirely new AI apps: https://github.com/jmorganca/oll.... Would love any feedback from you as we work on making Ollama better 😊.

Report

2yr ago

André J

How much ram do I need to run this? Any other hw specs needed?

Report

2yr ago

Michael Chiang

Kitematic

@sentry_co it depends on which model you want to run, an 8GB macbook pro M1 would be able to run the 'default' 7B llama 2 model (albeit with swap) 16GB M1 Macbook is what I have, and I can run 13B models just fine. 70B models, we've had good success with 64GB mac studios.

Report

2yr ago

André J

@mchiang0610 Thanks! Ill make my order a 64gb MacBook. And reference this reply :D joke aside. what's swap?

Report

2yr ago

Bryan Lee

Stackfiles

Congrats on the launch! I've been using this for the past couple of weeks and it's the easiest way to start using LLMs locally.

Report

2yr ago

Brand API — Speed up your onboarding with 1 API call

Speed up your onboarding with 1 API call

Promoted

Do you use Ollama?

Forum Threads

p/ollama

Kim Hallberg

•

2d ago

Ollama Turbo now in preview

Introduced with the release of Ollama's support for @GPT OSS, is Turbo; Ollama's privacy-first datacenter-grade cloud inference service.

Whilst it's currently in preview, the service costs $20/m, and has both hourly and daily limits. Usage-based pricing will be available soon. So far, the service only has gpt-oss-12b and gpt-oss-120b models, and works with Ollama's App, CLI, and API.

View all

Ollama

The easiest way to run large language models locally

The easiest way to run large language models locally

Ollama

The easiest way to run large language models locally

The easiest way to run large language models locally

Similar Products

Do you use Ollama?

Forum Threads

Ollama Turbo now in preview

Do you use Ollama?

Forum Threads

Ollama Turbo now in preview

You might also like