Skip to main content
Mole
Overview Features Testimonials Pricing FAQ Blog
EnglishEN 简体中文中 繁體中文繁 日本語日 한국어한 FrançaisFR DeutschDE ItalianoIT EspañolES
Buy now Download
Home/Blog/Clean Up Ollama and LM Studio Models on Mac

Developer

Clean Up Ollama and LM Studio Models on Mac

July 18, 2026 · 4 min read

Local AI tools can fill a disk quickly because model weights are the product, not a small cache around it. A model may be downloadable again, but the download can be expensive, a revision can disappear, or its license and access can change. Inventory models through the owning tool and preserve chats, fine-tunes, adapters, prompts, and project data separately.

Where local AI tools store their weight

The models are almost always the heavy part, and each one is measured in gigabytes.

  • Ollama keeps models in ~/.ollama/models by default, or in the directory set by OLLAMA_MODELS. List what you have with ollama list, and remove one by name with ollama rm <model>, which is safer than deleting files by hand because it updates Ollama's index too.
  • LM Studio lets you choose the models directory. Use My Models in the app or lms ls to list local models and sizes, then remove a model through LM Studio so the app's catalog remains consistent. Do not rely on one hardcoded hidden path.
  • Hugging Face libraries cache downloads in ~/.cache/huggingface/hub, which grows as scripts pull models and datasets. hf cache ls inventories revisions; preview removals with hf cache rm --dry-run, and use hf cache prune for unreferenced revisions.

Check the totals directly so you know what you are dealing with:

du -sh ~/.ollama/models ~/.cache/huggingface 2>/dev/null

Cache and data are not the same thing

This distinction keeps cleanup safe. A published model may be downloadable again, but a local fine-tune, adapter, converted quantization, or private checkpoint may not be. Desktop AI apps can also keep conversation state and attachments in Application Support or synchronize some history to an account. Check the app's export and sync behavior rather than assuming either that every chat is local or that every local file is disposable. Model caches are large, but they are not free to recreate.

Removing an AI app completely

If you are done with a tool, the app bundle is the small part. To reclaim the real space you have to remove its models and support files too, the same problem as uninstalling any app completely. For Ollama, remove named models with ollama rm before uninstalling the app. For LM Studio, remove models from its configured directory through the app. For a desktop chat client, export needed history and follow the vendor's uninstall guidance before reviewing support data. Do not delete an entire Application Support container merely because its name matches an app.

Under the hood: how the tools store models, and why size is inherent

Ollama keeps each model as content-addressed blobs (files named by their sha256 hash) under ~/.ollama/models/blobs, with small manifests that link a model name and tag to the blobs it needs. Two models built on the same base layer share blobs, so ollama rm deletes a manifest first and frees a blob only once nothing else references it. That is exactly why deleting blob files by hand is risky: you can orphan a model that still points at them. The size is not overhead, it is the model: billions of parameters still require gigabytes even after quantization, and larger or higher-precision models require far more, because the weights are the thing. Hugging Face's cache works the same way, storing immutable snapshots keyed by revision so repeated pulls deduplicate. This is why the rule is "remove through the tool's own command": it keeps the content-addressed store consistent instead of leaving dangling blobs.

Two named model manifests point into a shared pool of hash-named blobs, one blob referenced by both, so removing a model frees a blob only when it is no longer referenced.
Local model tools use a content-addressed store: models share blobs, so removing one frees space only for the blobs nothing else references, which is why the tool's own remove command keeps it consistent.

Where a disk map helps

A disk map such as Mole's Analyze view can reveal an unexpected model store, but model names, shared blobs, and revision references belong to Ollama, LM Studio, or Hugging Face. A general cleaner should avoid model stores and chat transcripts unless the user identifies an exact target.

A safe order of operations

List models with their owning tool, distinguish published weights from private or locally transformed artifacts, export unique conversations and adapters, then remove one named model at a time. Recheck disk use because shared blobs may limit the space reclaimed. Remove whole support directories only as part of a verified uninstall with no data left to preserve.

Mole brings disk analysis, app maintenance, and review-first cleanup into one native app, while leaving system-owned data to macOS and the apps that own it.

Buy Mole Try it free

Keep reading

  • DeveloperClean Up Xcode Without Losing Release Artifacts3 min read
  • DeveloperClean Up Docker on Mac Without Losing Data3 min read
  • DeveloperClean Up Homebrew Safely3 min read

Mole · 鼴

Cleanup, software, and status for your Mac.

v1.11.0 · Release notes

Support

Help Documentation Releases

Legal

Terms of Service Privacy Policy Refund Policy

Resources

Blog CLI Tool Affiliates Program

Connect

Twitter hi@mole.fit

Only official site mole.fit · Fake sites may ship unsafe downloads

For your Mac, or a friend's. The CLI stays free for terminal workflows. May your time be your own.