Install Ollama

Local LLM runtime. Unlocks bigger models (Llama 3.1 8B, Mistral, Qwen) than the in-browser Llama 3.2 1B.

Easiest path: download & double-click

Pick the build for your OS. The installer is signed by the vendor, so Windows SmartScreen / macOS Gatekeeper will let it run after a click-through.

Windows PowerShell. Paste & run.

winget install Ollama.Ollama; Start-Sleep -Seconds 3; ollama pull llama3.1
Open Windows Terminal or PowerShell, paste the line above, hit Enter. The script handles Python check, install, and model download.

macOS Linux Terminal. Paste & run.

curl -fsSL https://ollama.com/install.sh | sh && ollama pull llama3.1
Open Terminal, paste, hit Enter.

Paste this into Claude Code (works in Cursor / Codex / Cline too)

Open Claude (the desktop app or web), click + New session, switch to the Code tab, then paste the prompt below as your first message. Claude does the install, downloads, and verification for you. No terminal commands you have to type yourself.

Get Claude (free) Claude Code quickstart 
Install Ollama on this machine and pull the llama3.1 model so I can use it with Phantomline.

1. Detect my OS (Windows / macOS / Linux).
2. Install Ollama using the official installer (winget on Windows, the install.sh script on macOS/Linux, or download the .dmg/.exe if scripts aren't available).
3. Wait for the Ollama daemon to start (it runs at http://localhost:11434).
4. Run `ollama pull llama3.1` to download the default Phantomline model (~4.7 GB).
5. Verify by running `ollama list` and confirming llama3.1 appears.
6. Tell me when it's done so I can reload http://localhost:5000/app and see it marked READY.
What Claude will do for you:
  1. Detect your OS
  2. Check whether prerequisites are installed (Python, Git, etc.)
  3. Install anything missing
  4. Install Ollama and download model weights
  5. Verify the install worked
  6. Tell you when it's done
You'll see Claude ask for permission before running each install command. You can approve all or step through.

1Download the installer

Go to ollama.com/download and grab the build for your OS (Windows .exe, macOS .dmg, or Linux script).

Step 1 screenshot

2Run the installer

Double-click the .exe / .dmg, or pipe the Linux script into sh. Default options are fine. After install, Ollama runs as a background service. You'll see a small llama icon in your system tray.

curl -fsSL https://ollama.com/install.sh | sh
Step 2 screenshot

3Pull the default model

Open a terminal/PowerShell after install and run the command below. Llama 3.1 is ~4.7 GB so this takes 5-15 min depending on your connection.

ollama pull llama3.1
What you should see » 
pulling manifest
pulling 6a0746a1ec1a... 100% ▕████████▏ 4.7 GB
pulling 4fa551d4f938... 100% ▕████████▏  12 KB
verifying sha256 digest
writing manifest
success
Step 3 screenshot

Verify it worked

Run this in a terminal. It should list llama3.1 (size ~4.7 GB).

ollama list
Then: Reload /app — the readiness checklist will flip Ollama to READY.
Stuck? Email support@phantomline.xyz with your OS and the error and we'll send you exact steps.