omm uninstall
Remove a model and clean up every symlink and manifest entry it left behind — or preview exactly that with --dry-run first.
01 / 06
Overview
Reach for uninstall once you're done with a model. Pass all to remove every model omm has installed in one pass. --dry-run answers "what would this actually do" without deleting anything — worth reaching for first if you're not sure exactly what all currently covers.
02 / 06
Options
Every flag this command accepts, and what it defaults to when you leave it out.
<name> | all—Default: requiredAn installed model's filename, a numeric index from the last search or list run, or the literal word all.
--dry-run—Default: offShow what would be uninstalled without removing anything.
03 / 06
Examples
From a plain search to something you'd put in a script.
Uninstall one model.
$ omm uninstall qwen2.5-0.5b-instruct-q4_k_m.ggufPreview it first — nothing is removed.
$ omm uninstall qwen2.5-0.5b-instruct-q4_k_m.gguf --dry-runPreview uninstalling everything omm has installed.
$ omm uninstall all --dry-runUninstall by the number the last search or list run printed.
$ omm uninstall 104 / 06
A real run
Real omm uninstall qwen2.5-0.5b-instruct-q4_k_m.gguf --dry-run capture, 2026-08-24, this dev machine.
06 / 06
If something goes wrong
Every message below is one this command actually prints. Find yours, read why it happened, then do the last line.
zzzz-fake-model-xyz is not installed via omm. See `omm list`.- why
- This name doesn't match anything omm has installed — misspelled, or never installed through omm in the first place.
- what to do
- Run omm list to see the exact filename omm knows about.
- source
- src/omm/cli.py:5008-5013
Run `omm search` or `omm list` first to install/uninstall by number.- why
- A numeric index only means something after a search or list run in the same terminal printed one — there's nothing to resolve it against yet.
- what to do
- Run omm search or omm list first, then use the number it printed.
- source
- src/omm/cli.py:3057-3059
Still stuck? Open an issue with the exact message you saw.
All commands
- omm searchFind a model across the curated catalog, HuggingFace and ModelScope.
- omm installDownload a model into the hub and link it into every installed runner.
- omm runChat with an installed model — in the terminal for Ollama, or by opening the app for GUI runners.
- omm recommendGet a model suggestion ranked for this machine's hardware, with an offer to install it.
- omm contributeBenchmark models in a loop, uploading telemetry to improve recommend for hardware like yours.
- omm setupRe-run the hardware scan and runner-install checklist, any time.
- omm scanPrint this machine's hardware, detected runners, and models — no flags needed.
- omm tuneGet recommended context length, GPU offload, threads, and batch size for a model.
- omm fitSee whether a model fits this machine's free memory right now, installed or not.
- omm helpShow omm's own command summary, or the full reference with --all.
- omm importAdopt .gguf files sitting in other apps' model directories into the omm hub.
- omm listShow every model omm has installed and which runners each is linked into. Alias: ls.
- omm infoShow full detail — repo, version, size, links, run commands — for one installed model.
- omm upgradeRefresh installed models against their source — only re-downloads what's actually changed. Alias: up.
- omm linkRe-verify and repair every installed model's runner links, or link into a custom directory.
- omm cleanupClean up leftover partial downloads and broken runner symlinks in one pass — no flags needed.
- omm verifyProve that an installed model actually loads and generates text on this machine.
- omm benchmarkLocal quality and speed smoke evidence for one or more installed models.
- omm updateReinstall omm from the latest source and refresh its recommendation data.
- omm settingView or change omm's settings — telemetry, outbound data, theme, update channel, and more.
- omm doctorDiagnose the omm install and Ollama links, read-only — no flags needed.
- omm engine installInstall one local AI runner program directly, skipping the setup checklist.
- omm logRead the local run log: what omm ran, when, and whether it worked.
- README — UsageEvery omm command, one line each.