Tensor Archive Download
Tensor Wiki6 min read

Where are LM Studio models saved? Identify them before you move them

The reliable first answer is not a guessed operating-system path. Ask LM Studio which downloaded models it currently sees: the documented lms ls command lists local models, their size, architecture and parameters. That gives you an inventory before you touch storage.

Model files, local folders and archive media kept as distinct parts of one library.
Find the local data first; decide what to retain second.

Identify the models LM Studio knows about

LM Studio’s CLI documents lms ls for listing models downloaded in the local installation. It can list all models, filter LLMs or embedding models, show detailed information and produce JSON. Use it as the source of truth for the model set the running application recognizes.

A file-browser path may still be useful, but it is not enough by itself: application versions, import choices and configured directories can change how a model is arranged on disk. Start with the visible inventory, then use the app or CLI workflow to investigate a specific model.

Import local files without an accidental move

LM Studio documents lms import for bringing a local model file into its models directory. By default, import moves the file. When you need to preserve the source, the documented command supports copy, hard-link and symbolic-link options; it also supports a dry run to show what it would do first.

Read the verb before you run it. “Import” can mean move, copy or link depending on the selected option. If a file is your only working copy, choose a preservation path first and verify the model remains usable after the operation.

Make a storage decision after the runtime decision

LM Studio needs its active model files where it expects them. Tensor Archive does not replace that runtime directory or make the runtime discover an archive automatically. Its role begins when you have identified a completed related family you want to retain and recover later.

For example, you may keep a completed group of related local releases, test their archive and restore, then reclaim an old duplicate working copy manually. That is different from moving a live LM Studio model because the disk is full.

A safe sequence

  1. Run lms ls and identify the downloaded models and their approximate disk use.
  2. Use the documented import workflow and dry run before changing the location of a local file.
  3. Confirm LM Studio can still load the model before removing an earlier copy.
  4. For completed related artifacts, archive, verify and restore a separate copy before manual reclamation.

For another local runtime, see where Ollama stores models. For a broader first cleanup, use the model-library retention checklist.

Sources