LLM Cleaner scans your Mac for every local AI model — Ollama, LM Studio, Hugging Face, Whisper, ComfyUI, AI coding caches, and custom folders — then shows you exactly what is eating your disk so you can clean it up with confidence.
One scan. Full picture. Every cleanup action is reversible until you decide otherwise.
One click searches across Ollama, LM Studio, Hugging Face, Whisper, ComfyUI, AI coding caches, and any custom folder you add. No manual path hunting — it finds models wherever they ended up.
Sort by size, filter by tool, spot duplicates (verified by content hash — not just file size), and flag 10 GB+ models. Every row shows name, source, path, size, and last modified date.
Move to Trash (not permanent delete), move to an external drive with a symlink so your tools still work, or export a full Markdown report before touching anything.
Ollama, LM Studio, Hugging Face, Whisper, ComfyUI, and AI coding assistants scatter multi-gigabyte model files across hidden system folders. One download, one experiment, one forgotten quantization — and suddenly 40 GB is gone with no easy way to find it.
A single 7B model takes 4–8 GB. Run a few experiments and your SSD quietly fills up.
Seven different apps, seven different hidden cache directories. Nothing tells you the total.
Delete the wrong blob directory and Ollama loses track of models it thought it had.
These are real file sizes from Hugging Face. One experiment. One forgotten download. One duplicate. That is how 80 GB disappears.
Running the same writing or vision model in both Ollama and LM Studio? That is a duplicate sitting on your SSD. LLM Cleaner finds it.
Built specifically for local AI power users — all features are available from day one, not gated behind a roadmap.
Ollama, LM Studio, Hugging Face, Whisper, ComfyUI, AI coding caches (Cursor, Claude Code, Codex, Copilot), and loose files — plus any custom folder you add. Finds models even in non-standard locations via $OLLAMA_MODELS, $HF_HOME, and ComfyUI's extra_model_paths.yaml.
Identifies models stored twice across different tools using a partial content hash — not just file size matching. Catching the same 13B model in both LM Studio and Hugging Face cache is the most common way to recover 10+ GB instantly.
Move any model (or batch of models) to an external SSD with one click. LLM Cleaner leaves a symlink at the original path so Ollama, LM Studio, and every other tool keeps working without any reconfiguration.
Nothing is permanently deleted without two confirmations. Move to Trash, find the item still listed in the app with an "In Trash" badge, and restore it in one click if you change your mind.
Cursor, Claude Code, GitHub Copilot, and Codex download and cache model files you never explicitly asked for. LLM Cleaner finds these hidden caches and shows you exactly how much space they are using.
Generate a complete inventory of every model found — source, path, size, modified date, and duplicate flags — saved as a Markdown file on your Desktop. Useful before any bulk cleanup.
LLM Cleaner covers every major tool people actually run locally — including the ones that hide their caches where you'd never think to look.
Ollama
LM Studio
Hugging Face
WhisperEvery model below can be downloaded and cached on your Mac by tools like Ollama, LM Studio, Hugging Face, or ComfyUI. LLM Cleaner detects them all — including ones you downloaded months ago and forgot about.
Not seeing a model you use? Add its folder with + Folder and LLM Cleaner will scan it on the next run.
Pay once, use forever. All current features included and updates through v1.x. No renewal fees, no usage limits.
Price may increase after the early launch period.
By downloading you agree to our Terms of Use.
Full feature parity for Windows — same scanners, same safe cleanup flow, native desktop app.
Detect and manage models stored inside Docker volumes used by local AI tools and self-hosted LLM servers.
Automatically surface models you haven't used in 30+ days and give you a one-click review queue.
LLM Cleaner is a local desktop utility. It has no backend, no account system, and no telemetry. Your models stay on your machine.
No. LLM Cleaner moves files to Trash first — the same macOS Trash you already use. Review them, restore them, or empty the Trash whenever you're ready. Nothing is permanently deleted without your confirmation.
Never. LLM Cleaner runs entirely on your machine. No files leave your disk, no data is sent anywhere. The only network call it makes is a version-check ping to getllmcleaner.com.
It respects $OLLAMA_MODELS and $HF_HOME environment variables automatically. You can also add any folder manually using the custom folder button — it remembers your paths between scans.
Yes. The Move to Drive feature copies files to your chosen external drive and leaves a symlink at the original location. Ollama, LM Studio, and other tools keep working without any configuration change.
Ollama · LM Studio · Hugging Face · Whisper · ComfyUI · AI coding caches (Cursor, Claude Code, Codex, Copilot) · loose files anywhere on disk. Detects .gguf, .safetensors, .bin, .pt, .ckpt, .pth, and .mlx files.
The current release is macOS only (Apple Silicon + Intel). Windows support is planned for a future version.
Both. Developers get full path visibility, a Markdown export report, and source-by-source breakdown. Beginners get a safe, guided cleanup flow — nothing disappears unless you explicitly confirm it.
One scan. Every AI model. Every tool. Fully recoverable cleanup.