omm fit
Show whether a model — installed or not — fits this machine's memory right now, as a bar over what other apps are using.
01 / 06
Overview
Reach for fit when you want a live answer, not a cached one: unlike the fit check inside install, this reads memory availability at the moment you run it, so the same model can read differently five minutes later if other apps opened or closed. It works on models that aren't installed yet too, as long as their size can be resolved from the provider.
02 / 06
Options
Every flag this command accepts, and what it defaults to when you leave it out.
<name>—Default: requiredAn installed model's filename, a curated name, or a repo reference whose size the provider reports.
03 / 06
Examples
From a plain search to something you'd put in a script.
The fit card for an installed model.
$ omm fit qwen2.5-0.5b-instruct-q4_k_m.ggufThe same numbers as JSON — useful in a script's fit check before installing.
$ omm fit qwen2.5-0.5b-instruct-q4_k_m.gguf --jsonWorks on a model that isn't installed yet, as long as its size is known.
$ omm fit mistral-7b-instruct-q404 / 06
A real run
Real omm fit qwen2.5-0.5b-instruct-q4_k_m.gguf 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.
Could not determine the size of oversized-405b-q4_k_m.gguf (not installed, and the provider did not report a file size).- why
- The model isn't installed, and its provider didn't report a file size fit could use to estimate memory — this happens for some direct-URL or unusual repo references.
- what to do
- Install it (fit's own check runs first, so nothing downloads if it clearly won't fit) or search for it by name to find a reference with size metadata.
- source
- src/omm/cli.py:5608-5611
--json has no effect on `omm fit` - ignoring it.- why
- This is a real, verbatim warning omm itself prints — fit's own code does branch on --json and prints structured output correctly (see the captured JSON example above); the warning is a known mismatch in the flag-handling decorator's own bookkeeping, not a sign the flag actually failed.
- what to do
- Nothing to do — the JSON output is correct regardless of this warning.
- source
- src/omm/cli.py global_flags decorator
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 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 uninstallRemove a model and clean up its symlinks and manifests. Alias: rm.
- 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.