This document explains how to set up **Continue.dev + Ollama** locally
on your computer, enabling VSCode with Cursor-like AI capabilities:
scanning projects, chatting, and modifying files.

## 1. Install Ollama
---
1. Download and install from [Ollama website](https://ollama.com/download) (macOS / Linux / Windows).
2. Verify installation:

ollama --version

## 2. Install Models
---
1. Download the code-specialized model and an embedding model

# Qwen 2.5 Coder 7B (code-focused model)
ollama pull qwen2.5-coder:7b

# Embedding model (used by Continue.dev for repo context)
ollama pull nomic-embed-text

## 3. Start Ollama Server
---
1. Start Ollama:

ollama serve

or (macOS GUI)

open -a Ollama

Test the API:

curl http://127.0.0.1:11434/api/tags

## 4. Install Continue.dev
---
1. In VSCode, search for **Continue** in Extensions and install.\
2. Open the config file (usually `~/.continue/config.json`) and add:

{
    "models": [
        {
            "title": "Qwen2.5 Coder (7B) - Local",
            "provider": "ollama",
            "model": "qwen2.5-coder:7b",
            "apiBase": "http://127.0.0.1:11434"
        }
    ],
    "tabAutocompleteModel": {
        "provider": "ollama",
        "model": "qwen2.5-coder:7b",
        "apiBase": "http://127.0.0.1:11434"
    },
    "embeddings": {
        "provider": "ollama",
        "model": "nomic-embed-text",
        "apiBase": "http://127.0.0.1:11434"
    },
    "contextProviders": [
        "file",
        "directory",
        "git",
        "terminal",
        "selection",
        "codebase"
    ],
    "allowAnonymousTelemetry": false
}

## 5. Verify the Model is Running
---
### Method 1: Ollama command

ollama ps

### Expected output if running:

NAME ID SIZE STATUS
qwen2.5-coder:7b abcd123 4.7GB running

### Method 2: API test

curl http://127.0.0.1:11434/api/generate -d 
'{
	"model": "qwen2.5-coder:7b",
	"prompt": "hello world"
}'

### Method 3: System monitoring
- Check CPU and memory usage.

ps aux | grep ollama

## 6. Usage
---
1. In VSCode, open Continue panel and select **Qwen2.5 Coder (7B) - Local**.
2. Type your request, for example: Modify src/utils/date.ts so parseDate supports both YYYY/MM/DD and ISO 8601.
3. Continue.dev will display a patch → click **Apply** to update the file.
4. For multi-file automatic edits → switch to **Agent Mode**.
## 7. Troubleshooting
---
- **Model not found**: Make sure the name is correct → `qwen2.5-coder:7b`.
- **Server not running**: Ensure `ollama serve` or GUI app is open.\
- **No response in Continue.dev**: Check `config.json` `apiBase`, use `127.0.0.1:11434`.
- **Too slow**: Try a smaller model, or upgrade to `qwen2.5-coder:14b`/ `llama3.1:8b`.