Get a model running on your computer, then ask it to draft an email.
A model is a file. An app opens that file and lets you talk to it. This guide uses Hugging Bay, our free app. It comes with Tug, an assistant that picks a model for your computer and runs it.
1. Get the app
Download Hugging Bay for Linux
Install it and open it.
2. Pick a model
Ask Tug for a small chat model, or search the app for Qwen2.5-1.5B-Instruct-GGUF. Download it and wait until it finishes.
Want to look first? Find a model for my computer
3. Run it on your computer
Type the example below into the message box and send it.
Write a short, friendly email asking to move our meeting to Friday.
You're running a model when its reply appears. Read the draft and check its details before using it.
Help if the model will not load
Prefer LM Studio?
LM Studio is a separate free app that opens GGUF model files. It recommends 16 GB of memory. Check LM Studio requirements
- Download LM Studio for Linux, install it and open it.
- Open Discover. Search for Qwen2.5-1.5B-Instruct-GGUF. Choose Q4_K_M only if the app marks it as supported, then click Download.
- Open Chat, select the model at the top, wait for it to load, then send the example above.
Already downloaded a model file from Hugging Bay? Open a downloaded model file
Other apps and source instructions
Ollama: setup and first chatJan: setup and first chat
App requirements and controls can change. Check their instructions if your screen differs.