Ollama

The easiest way to run large language models locally

5.0•25 reviews•

1.1K followers

The easiest way to run large language models locally

5.0•25 reviews•

1.1K followers

Visit website

AI Infrastructure Tools

•

LLM Developer Tools

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

Have a question about Ollama? Ask it here and get a real answer.

AppSignal — Get the APM insights you need without enterprise price tags.

Get the APM insights you need without enterprise price tags.

Promoted

Ollama Launches

Ollama Desktop App The easiest way to chat with local AI

Launched on August 1st, 2025

Ollama v0.7 Run leading vision models locally with the new engine

Launched on May 19th, 2025

Do you use Ollama?

Forum Threads

p/ollama

•

5mo 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

Newsletter Apps About FAQ Terms Privacy & Cookies Privacy Choices Advertise llms.txtContact us: hello@producthunt.com

5.0

Based on 25 reviews

Review Ollama?

Makers consistently praise Ollama for fast local iteration, privacy, and control. The makers of

Sequoia

liken it to an in-house AI lab with zero latency and no GPU bills. The makers of

Portia AI

call it a universal connector for local models in their SDK, while the makers of

Znote

highlight secure, offline use. Users echo the simplicity—easy setup, Docker-like workflows, quick prototyping, solid performance, and cost savings. Some note best results with mid-size models and smooth integrations via APIs.

+22

Summarized with AI

Pros

local AI model deployment (11)

easy to use (6)

no third-party API reliance (3)

AI server hosting (2)

data privacy (2)

Pros

Cons

Reviews

All Reviews

Most Informative

•1 review

What's great

easy to use (6)local AI model deployment (11)

I switched to Ollama from clunkier solutions and I have no regrets. Multimodal model support is well-implemented - feeding images through the API is just as easy as text. It’s great that the project is evolving so fast; support for new models usually pops up almost the day after they drop on Hugging Face. This is the simplest way to "play around" with modern AI locally without the headache of setting up the environment.

What needs improvement

I’d love to see a simpler way to import my own .gguf files downloaded outside the official Ollama library, without having to manually define all the parameters in a Modelfile.

How much disk space do common models require locally?

Typically, popular medium-sized models (7B-8B parameters) like Llama 3 or Mistral take up about 4.5-5 GB in standard 4-bit quantization

How simple is creating and customizing your own models?

It's simple using the Modelfile system, the process is very similar to writing a Dockerfile

Ratings

Ease of use

Reliability

Value for money

Customization

Report

1 view3d ago

•2 reviews

What's great

easy to use (6)local AI model deployment (11)no third-party API reliance (3)

Super easy to use tool to launch self hosted llm, even for other AI tools.

What needs improvement

Image generation is still not available at this time.

vs Alternatives

No idea about alternatives, and sincerely I don't feel I need one

How smooth is installation on macOS, including Apple Silicon?

just a bash file

How easy is switching between different pre-built models?

Just a bash command, super easy. Also, if you launch a model you don't have, Ollama will download it for you

What costs arise beyond the free tier, if any?

No other costs

Ratings

Ease of use

Reliability

Value for money

Customization

Report

9 views2mo ago

used this to build

Sequoia Health 2.0

(330 points)

•11 reviews

We’re exploring Ollama to test and run LLMs locally—faster iteration, zero latency, total control. It’s like having our own AI lab, minus the GPU bills

What's great

fast performance (1)local AI model deployment (11)no third-party API reliance (3)AI server hosting (2)

Report

6 views6mo ago

•1 review

What's great

easy to use (6)local AI model deployment (11)

What needs improvement

I’d love to see a simpler way to import my own .gguf files downloaded outside the official Ollama library, without having to manually define all the parameters in a Modelfile.

How much disk space do common models require locally?

Typically, popular medium-sized models (7B-8B parameters) like Llama 3 or Mistral take up about 4.5-5 GB in standard 4-bit quantization

How simple is creating and customizing your own models?

It's simple using the Modelfile system, the process is very similar to writing a Dockerfile

Ratings

Ease of use

Reliability

Value for money

Customization

Report

1 view3d ago

•2 reviews

What's great

easy to use (6)local AI model deployment (11)no third-party API reliance (3)

Super easy to use tool to launch self hosted llm, even for other AI tools.

What needs improvement

Image generation is still not available at this time.

vs Alternatives

No idea about alternatives, and sincerely I don't feel I need one

How smooth is installation on macOS, including Apple Silicon?

just a bash file

How easy is switching between different pre-built models?

Just a bash command, super easy. Also, if you launch a model you don't have, Ollama will download it for you

What costs arise beyond the free tier, if any?

No other costs

Ratings

Ease of use

Reliability

Value for money

Customization

Report

9 views2mo ago

used this to build

Sequoia Health 2.0

(330 points)

•11 reviews

We’re exploring Ollama to test and run LLMs locally—faster iteration, zero latency, total control. It’s like having our own AI lab, minus the GPU bills

What's great

fast performance (1)local AI model deployment (11)no third-party API reliance (3)AI server hosting (2)

Report

6 views6mo ago

Ollama

The easiest way to run large language models locally

The easiest way to run large language models locally

Have a question about Ollama? Ask it here and get a real answer.

Ollama Launches

Do you use Ollama?

Forum Threads

Ollama Turbo now in preview

Trending categories

Top reviewed

Trending products

Top forum threads

Trending categories

Top reviewed

Trending products

Top forum threads

Have a question about Ollama? Ask it here and get a real answer.

Ollama Launches

Do you use Ollama?

Forum Threads

Ollama Turbo now in preview

What's great

What needs improvement

How much disk space do common models require locally?

How simple is creating and customizing your own models?

What's great

What needs improvement

vs Alternatives

How smooth is installation on macOS, including Apple Silicon?

How easy is switching between different pre-built models?

What costs arise beyond the free tier, if any?

What's great

What's great

What needs improvement

How much disk space do common models require locally?

How simple is creating and customizing your own models?

What's great

What needs improvement

vs Alternatives

How smooth is installation on macOS, including Apple Silicon?

How easy is switching between different pre-built models?

What costs arise beyond the free tier, if any?

What's great