Learn deep learning onthe computer you already own.
DeepLM runs a small AI model on your machine and reads your real hardware. Ask what your GPU can do, why a model fits or doesn't, and what the terms mean.
curl -fsSL https://deeplm.ai/dlm-ops-dev/install.sh | bash -s -- --my-machineOne command on macOS or Ubuntu. No GPU? It runs on your CPU too.
Read the docs
Paste the command above into a terminal on macOS or Ubuntu. It installs Docker if you need it, picks the best way to run the model, and opens DeepLM in your browser. Windows users can follow the Windows guide.
- Installs Docker if you do not have it
- Picks the best way to run the model: your Mac’s GPU, an NVIDIA GPU, or the CPU
- Downloads DeepLM Ops (the 2.55 GiB model comes down on the first start)
- Starts it and opens it in your browser
Safe to re-run: the same command upgrades or restarts it. This is 0.2.0-rc.4, a release candidate for testing. Want to see what it does first? Read the script.
On Windows? The one-line installer supports macOS and Ubuntu. Follow the Windows guide.
Option: add --no-open after --my-machine to print the sign-in link instead of opening a browser.
The sign-in link it prints is a password and works until the container restarts. Don't paste it into chats, issues or screen shares.
Examples
Try asking
- What GPU do I have, and how much memory does it have?
- Will Llama 3.1 8B fit on my GPU?
- What does quantization change about a model?
- What's using my GPU right now?
Why DeepLM
It sees your real hardware
Answers come from live readings of your GPU, memory, and running processes.
It checks before you download
Ask whether a model fits in GPU memory before you pull it.
It stays on your machine
The app serves on 127.0.0.1 and sends no telemetry.
It can’t change anything
Every tool is read-only, so you can explore safely.