Early access 路 FREE 路 runs on your machine
Run local AIon the 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.
macOS 路 Ubuntu
curl -fsSL https://deeplm.ai/dlm-ops-dev/install.sh | bash -sOne command on macOS or Ubuntu. No GPU? It runs on your CPU too.
Read the docs127.0.0.1:8090
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's free
Download it and use it on your machine without any subscription.
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鈥檛 change anything
Every tool is read-only, so you can explore safely.
Partners
