IDE Extensions

Native Ollama integrations for popular development environments

Ollama integrates natively with popular IDEs and code editors, providing AI assistance directly in your development environment.

VS Code

Microsoft’s Visual Studio Code has built-in support for Ollama through the Copilot sidebar.

Setup

1. Open Copilot sidebar

   Click the Copilot icon in the top-right window

   
2. Select model dropdown

   Click Manage models

   
3. Add Ollama provider

   Enter Ollama under Provider Dropdown and select your models

   

Recommended Models for VS Code

• qwen3 — Efficient all-purpose model
• qwen3-coder:480b-cloud — Advanced cloud code generation
• glm-4.7 — Local reasoning model

Tips

Use cloud models for large context windows when working with entire files or projects.

---

JetBrains IDEs

IntelliJ IDEA, PyCharm, WebStorm, and other JetBrains IDEs support Ollama with an AI subscription.

To use Ollama with JetBrains IDEs, you need a JetBrains AI Subscription.

Setup (IntelliJ Example)

1. Open AI chat

   Click the chat icon in the right sidebar

   
2. Set up local models

   Select the current model → Set up Local Models

   
3. Configure Ollama

   Under Third Party AI Providers, choose Ollama

4. Set host URL

   Confirm Host URL is http://localhost:11434 → Ok

5. Select a model

   Choose a model under Local models by Ollama

   

Supported JetBrains IDEs

IntelliJ IDEA

Java, Kotlin, Scala development

PyCharm

Python development

WebStorm

JavaScript, TypeScript, Node.js

PhpStorm

PHP development

GoLand

Go development

RubyMine

Ruby development

The setup process is identical for all JetBrains IDEs.

---

Zed

Zed is a high-performance, collaborative code editor with native Ollama support.

Setup

1. Open assistant settings

   Click the star icon in the bottom-right corner → Configure

   
2. Select Ollama provider

   Under LLM Providers, choose Ollama

3. Connect to Ollama

   Confirm Host URL is http://localhost:11434 → Connect

4. Select a model

   Choose a model from the Ollama dropdown

   

Connecting Zed to ollama.com

1. Create API key

   Create an API key on ollama.com

2. Open Zed settings

   Click star icon → Configure

3. Set API URL

   Under LLM Providers → Ollama, set API URL to https://ollama.com

4. Add API key

   Enter your API key from step 1

---

Cline

Cline is a VS Code extension that provides an autonomous coding agent interface.

Setup

1. Install Cline

   Install Cline from the VS Code marketplace

2. Open Cline settings

   Open Cline settings → API Configuration

3. Set provider to Ollama

   Set API Provider to Ollama

4. Select a model

   Choose a model or type one (e.g., qwen3)

5. Update context window

   Set Context Window to at least 32K tokens

Coding tools require a larger context window (at least 32K tokens). See Context Length for configuration.

Recommended Models for Cline

• qwen3-coder:480b-cloud — Advanced code generation
• deepseek-v3.1:671b-cloud — Massive reasoning model
• glm-4.7 — Local reasoning and coding

Connecting Cline to ollama.com

1. Create API key

   Create an API key on ollama.com

2. Enable custom base URL

   In Cline settings, click Use custom base URL

3. Set URL

   Set base URL to https://ollama.com

4. Add API key

   Enter your Ollama API key

---

Other Extensions

Continue

Continue is an open-source AI code assistant for any IDE.

Setup: Add Ollama as a provider in Continue’s settings.

Cline CLI

Cline also provides a CLI tool that can be launched with:

ollama launch cline

See the Integrations Overview for details.

---

General Tips

Use Cloud Models

For large codebases, use cloud models with 100k+ context windows

Increase Context

Adjust context length for local models: Context Length

Model Selection

Choose specialized code models like qwen3-coder for best results

Performance

Smaller models (8B) are faster but less capable; balance based on needs

Context Window Configuration

Most IDE integrations work best with large context windows (32k-128k tokens).

For Local Models

ollama run qwen3-coder /set parameter num_ctx 65536

For Cloud Models

Cloud models automatically use their maximum context window.

See Context Length for detailed configuration.

Troubleshooting

Connection Failed

Verify Ollama is running:

ollama list

Models Not Appearing

Ensure models are pulled:

ollama pull qwen3
ollama list

Slow Performance

• Use cloud models for large context
• Use smaller local models for quick tasks
• Ensure sufficient VRAM for local models

IDE Can’t Find Ollama

Check the host URL is correct:

• Local: http://localhost:11434
• Remote: Your server’s URL
• Cloud: https://ollama.com

Next Steps

Try Coding Agents

Explore autonomous coding agents

API Documentation

Learn about Ollama’s APIs

Context Length

Configure model context windows

Model Library

Browse available models