Ollama

Ollama is a platform for running open models locally or in the cloud for automation, coding, analysis, and agent workflows. Includes downloads, model browsing, integrations, and pricing plans.

Développement Agents IA Outils Dev IA Modèles de Langage

Visiter le Site Web

Overview

Ollama is a platform for working with open models locally or in the cloud. The site positions it as a way to automate work with open models while keeping data private, and it supports workflows ranging from simple chat to coding, document analysis, and agent tasks.

The product combines local model execution with cloud access for larger or faster models. Its site surface includes model browsing, a download flow for desktop installation, documentation for integrations and APIs, and pricing tiers that separate unlimited local hardware use from metered cloud usage.

Core capabilities

Local and cloud model execution

Run models on your own hardware for offline or local workflows, with cloud models available when you need larger or faster systems.

Model discovery and selection

Choose from models for chat, coding, vision, embeddings, reasoning, and agentic workflows through the site’s model browsing experience.

Multiple access surfaces

Use Ollama through the CLI, API, desktop apps, and libraries, with documentation for integrations and first API requests.

App and agent integrations

Connect Ollama to apps, editors, and agents, including workflows highlighted on the home page for tools such as Claude Code and other agents.

Tool-aware cloud models

Access cloud models that are tested for tool calling and real agent workflows before release, according to the pricing FAQ.

Usage tiers for cloud work

Use paid cloud plans for heavier workloads, including concurrent model runs and larger models, while keeping local runs unlimited on your own hardware.

Practical use cases

Local private workflows
Run open models on a local machine when you need offline operation or want to keep sensitive work on your own hardware.
Heavier cloud-assisted work
Use cloud models for coding automation, document analysis, and other tasks that benefit from larger or faster models.
Integrating with tools and products
Connect Ollama to an app, editor, or agent through the documented integration and API paths to build model-powered workflows.
Choosing models for a task
Browse available models for chat, coding, vision, embeddings, and reasoning when selecting a model for a specific task.
Continuous multi-model sessions
Use paid plans for sustained work that needs multiple concurrent models or higher usage limits.

Pros and Cons

Pros

Supports both local hardware execution and cloud models.
Offers multiple ways to use the product, including CLI, API, desktop apps, and libraries.
Documents integrations and first-request workflows for apps, editors, and agents.
States that prompt and response data are not logged or trained on.
Provides separate cloud plans for lighter, heavier, and team-oriented usage needs.

Cons

Cloud usage is metered by plan, with limits and concurrency caps for paid tiers.
The source material does not give complete details for every integration, model, or setup workflow.

FAQ

Can I use Ollama locally and in the cloud?

Ollama supports running models locally on your own hardware, and its documentation also points to cloud models for larger workloads. The pricing page notes local hardware usage is unlimited, while cloud usage depends on the plan.

How do I connect Ollama to other tools?

The site says Ollama can connect to apps, editors, and agents, and its documentation includes integrations plus API references and Python and JavaScript libraries.

Do Ollama cloud models support tool calling?

The pricing page says cloud models that support tools are tested for tool calling and real agent workflows before they go live.

What platforms can I install Ollama on?

The download page offers installers for macOS, Linux, and Windows, and the Windows page notes Windows 10 or later is required.

Does Ollama train on my data?

No. The pricing page states that prompt or response data is never logged or trained on, and the home page says your data stays yours.

Quick Facts

Category: AI platform
Primary use: Run open models for automation, coding, analysis, and agents
Access: Local hardware plus cloud models
Platforms: macOS, Linux, Windows
Source domain: ollama.com
Pricing: Free local use; paid Pro and Max cloud plans; Team coming soon