omm
Package manager for local GGUF models that installs, links, ranks, and verifies them.
Tested on Linux
Use it
Linux x86_64
You need first
- Runtimes:
Python 3.10+ - Needs the network
pipx install omm-model per README
pipx install omm-model
Check that it works
omm --version 2>&1The output should contain “omm 0.4.84”.
First thing to try
omm list 2>&1Run omm list to see the models in your hub.
What it does
- Install GGUF models into a central hubTested
How to use it
- Put your .gguf files in a folder.
- Run
omm import <folder> --yesto import them into the hub. - Run
omm list --jsonto see the installed models.
- Rank models against your hardwareTested
How to use it
- Run
omm scan --jsonto see your RAM and other hardware details. - Run
omm fit <model name>to check whether a model fits your machine now.
- Run
- Link models across local AI runnersNot shown working
- Check that a model loads and generates textNot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- 2 of 4 features work
- Works offline
macOS and Windows: the project says it runs there; pickfit hasn’t tried it.
Good for
- install GGUF models into a central model hub
- rank models against live RAM, VRAM, OS and runner state
- verify local load and generation via Ollama or LM Studio
- recommend compatible models and install one
- chat with an installed model in the terminal
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
Linux x86_64
Its main function works
- Replayed from scratch
- Works offline
- Checked on 30 Oct 2026
- Version 0.4.84