SiftMac
Who it’s for · Updated 21 November 2026

What fills a Mac that runs local models and AI coding tools

By Mohit Nippanikar, who makes SiftMac

The short answer
On this page
  1. What fills an AI developer’s Mac
  2. What’s safe to clear, and what to keep
  3. How SiftMac helps an AI developer
  4. A cleanup routine for an AI developer’s Mac
  5. Questions

1. What fills an AI developer’s Mac

Most of it lands in hidden folders in your home folder, which is why the storage bar can’t name it. The usual parts:

WhatWhere it livesComes back?More
Ollama models~/.ollama/models, or wherever OLLAMA_MODELS pointsOnly with ollama pullOllama models
Hugging Face models and datasets, used by Transformers and MLX~/.cache/huggingface/hubDownloaded again on next useHugging Face cache
LM Studio models~/.lmstudio/modelsDownloaded againLM Studio models
PyTorch hub weights~/.cache/torch/hubDownloaded again—
Claude Code sessions and old versions~/.claude/projects, ~/.local/share/claude/versionsSessions no; old versions aren’t neededClaude Code’s folder
Codex sessions~/.codex/sessions, ~/.codex/history.jsonlNoCodex’s folder
Project chats in Cursor, Windsurf and AntigravityUser/workspaceStorage in each app’s Application Support folderNoAI files guide
Editor caches and installed updatesCache, Code Cache, GPUCache in each app’s folder; ~/Library/Caches/<app ID>.ShipItYesCursor’s ShipIt, extensions
ML Python environmentsEach project’s .venv, conda environmentsYes, from the requirements filePython environments
Apple Intelligence and Chrome’s Gemini Nano/System/Library/AssetsV2, Chrome’s OptGuideOnDeviceModelManaged by macOS and ChromeChrome’s model

Measure each tool’s folder, biggest last:

du -sh ~/.ollama ~/.cache/huggingface ~/.lmstudio ~/.cache/torch ~/.claude ~/.codex ~/.gemini ~/.local/share/claude 2>/dev/null | sort -h

Then list the models themselves, with sizes, and the Hugging Face repos nobody has used for a month:

ollama ls
hf cache ls
hf cache ls --filter 'accessed>30d'

2. What’s safe to clear, and what to keep

Models: remove with the tool, not Finder

Sessions and history: yours to judge

Caches, and what to leave alone

3. How SiftMac helps an AI developer

SiftMac’s AI files category is built for this kind of Mac:

It doesn’t clean ~/.cache/torch, conda environments or Docker volumes. The space map shows how big they are, and their own tools remove them.

4. A cleanup routine for an AI developer’s Mac

  1. Run ollama ls and hf cache ls, and note the models you used this month.
  2. Remove the rest with ollama rm and hf cache rm, then run hf cache prune for leftovers.
  3. Move the models you keep to an external SSD if the internal disk is small.
  4. Quit your editors and AI apps, then clear their caches and installed-update folders.
  5. Look through agent history you won’t resume: old Codex sessions, chats of deleted projects.
  6. Delete virtual environments of finished experiments, keeping each requirements file.
  7. Check free space before the next big pull: models arrive several gigabytes at a time.

Questions

Can I just delete ~/.cache/huggingface?

You can, but everything in it downloads again the next time code asks for it, and the datasets in the same cache go too. hf cache ls and hf cache rm let you remove only the models you’re done with.

Will deleting old Claude Code sessions break anything?

No. You lose the ability to resume or reread those sessions. Settings, CLAUDE.md files, skills and project memory are kept elsewhere and aren’t affected.

Should I delete Apple Intelligence’s models to make room for my own?

No. macOS manages them and brings them back, and there’s no supported way to remove them by hand. Free space from your own models and caches instead.

How SiftMac handles it. SiftMac lists each Ollama, Hugging Face and LM Studio model with when you last used it, old agent sessions after the age you choose, and AI apps’ caches; models are never ticked for you, and sessions wait 7 days on the Undo Shelf.

Download SiftMac · scanning is free, and so is your first 2 GB of cleaning · See how it works