The Tool Desk
Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →To reclaim disk space used by local AI models, first identify which app downloaded them and where it stores them, then remove only models or cache data you no longer need. Unloading a running model frees memory, not the disk space occupied by its downloaded files. Hugging Face provides documented, cache-aware removal and pruning commands; for Ollama and LM Studio, check the apps’ current model-management controls rather than deleting internal files by hand.
First, tell disk storage apart from memory
A model can occupy disk space while downloaded and use RAM or VRAM while loaded to run. Stopping or unloading it addresses the latter: Ollama documents ollama stop for unloading a model from memory, and LM Studio documents lms unload for the same purpose. Neither action is a documented way to delete the downloaded model files. Ollama’s FAQ and LM Studio’s CLI documentation describe these distinctions.
As an Amazon Associate I earn from qualifying purchases.
Find the app and actual model store
Start with the application or library you used to download the model. A computer can have separate stores for different tools; a model will not necessarily be in the Hugging Face cache just because it is a machine-learning model. The Hugging Face Hub cache is used by huggingface_hub and libraries that depend on it, including Transformers, Diffusers, Datasets, MLX, and vLLM. See Hugging Face’s cache documentation.
Hugging Face Hub cache
The documented default is ~/.cache/huggingface/hub. Check for overrides before looking there: HF_HUB_CACHE sets the Hub cache directory directly and takes priority; when HF_HOME is set, the Hub cache is under $HF_HOME/hub. The cache layout uses snapshots and shared, content-addressed blobs, so one file may serve more than one revision or repository.
#1 Best Overall
- Get NVMe solid state performance with up to 1050MB/s read and 1000MB/s write speeds in a portable, high-capacity drive(1) (Based on internal testing; performance may be lower depending on host device & other factors. 1MB=1,000,000 bytes.)
- Up to 3-meter drop protection and IP65 water and dust resistance mean this tough drive can take a beating(3) (Previously rated for 2-meter drop protection and IP55 rating. Now qualified for the higher, stated specs.)
- Use the handy carabiner loop to secure it to your belt loop or backpack for extra peace of mind.
- Help keep private content private with the included password protection featuring 256‐bit AES hardware encryption.(3)
- Easily manage files and automatically free up space with the SanDisk Memory Zone app.(5). Non-Operating Temperature -20°C to 85°C
Ollama model store
Ollama lists these default locations in its FAQ:
- macOS:
~/.ollama/models - Linux:
/usr/share/ollama/.ollama/models - Windows:
C:Users%username%.ollamamodels
If OLLAMA_MODELS is configured, Ollama uses that alternate model directory instead. Check the setting before inspecting or moving files.
LM Studio model inventory
LM Studio’s CLI can show downloaded model names and sizes. In a terminal where its CLI is available, run lms ls; use lms ls --detailed for more detail or lms ls --json for JSON output. The figures shown are an inventory of your own downloads, not an estimate of what models generally require. See the lms ls documentation.
Rank #2
- MADE FOR THE MAKERS: Create; Explore; Store; The T7 Portable SSD delivers fast speeds and durable features to back up any endeavor; Build your video editing empire, file your photographs or back up your blogs all in an instant
- SHARE IDEAS IN A FLASH: Don’t waste a second waiting and spend more time doing; The T7 is embedded with PCIe NVMe technology that brings fast read and write speeds up to 1,050/1,000 MB/s¹, making it almost twice as fast as the T5
- ALWAYS MAKE THE SAVE: Compact design with massive capacity; With capacities up to 4TB, save exactly what you need to your drive – from large working files to game data and everything in between
- ADAPTS TO EVERY NEED: Whether using a PC or mobile phone, count on the T7 for extensive compatibility²; It’s a true team player when it comes to heavy-duty application usage or file-saving
- HI RESOLUTION VIDEO RECORDING: Record Ultra High Resolution (4K 60fs) videos directly onto the T7 Portable SSD with your favorite camera or mobile devices; Supports iPhone 15 Pro Res 4K at 60fps video and more³
Choose the cleanup that matches what you want to remove
Remove selected Hugging Face downloads safely
Use the Hugging Face CLI cache commands rather than deleting files inside the cache yourself. Its snapshots can reference shared blobs, and cache-aware cleanup accounts for those references. The official cache management guide documents these options:
Quick wins for a faster PC:
Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Repair Windows errors before they cause bigger problemsFix Now →hf cache lslists cache entries. The Python cache scanner can also report total cache size and repositories and revisions, which helps you decide what is safe to remove.hf cache rm model/<repo-id>targets a repository. You can provide a revision hash to target a particular revision. The command requests confirmation by default; add--dry-runto preview the planned deletion and estimated space to be reclaimed before proceeding.- To remove one cached file, provide its exact
hf://file URI. This operation requires the exact file path; it does not accept a folder name or glob pattern. If a later run needs that file, it will be downloaded again. hf cache pruneremoves eligible cache leftovers: revisions no longer referenced by a branch or tag, partial.incompletedownloads, and shared blobs that are no longer used by any cached repository.
Review the preview and keep any repository or revision you still rely on. After cleanup, Hugging Face reports the space freed; the actual amount depends on which files were shared and what was removed.
Rank #3
- Capacity Display Variance: 500GB external ssd often appears as around 465GB on Windows. MacOS can show full 500 GB capacity. This is binary calculation difference and doesn’t affect SSD hard drive actual physical storage
- 1050 MB/s Speed: Instantly access to your files with blazing-fast 10Gbps external SSD read up to 1050MB/s and write up to 1000MB/s. LED Light indicates USB SSD instant activity
- Data Security: Solid state drives S.M.A.R.T. health diagnostics and adaptive TRIM optimizing data block management ensures consistent write speeds and extends the longevity of the portable SSD
- USB-C & USB-A Cable: Both cables featuring rapid USB 3.2 Gen2, this USB SSD effortlessly bridges devices, enabling seamless cross-platform file transfers and backup between computers, smartphones, tablets and iPhone
- Always Fast: No slowdowns for large file transfers. With SLC caching (25% of current available capacity allocated as high-speed cache), this external SSD delivers steady 10Gbps for transfers within the cache capacity
Remove Ollama or LM Studio downloads
For Ollama, confirm the model name and active store location, then use the current documented model-management controls in the Ollama CLI or application. The official FAQ establishes storage locations and the OLLAMA_MODELS setting, but the documentation reviewed here does not establish a disk-removal command. Do not guess a command or remove internal store files manually.
For LM Studio, use lms ls to identify downloads and their sizes, then use the current model-management controls in the app to remove a download if that option is available in your version. The CLI pages cited here establish inventory and unloading, not a disk-deletion command; lms unload alone only unloads a model from memory.
Rank #4
- NEARLY 2X FASTER THAN OUR PREVIOUS GENERATION(8) – move 1,000 high-res photos in under 60 seconds(6) with up to 2000MB/s transfer speeds(2).
- IP65 RATING AND UP TO 3M DROP PROTECTION(3) – protects against spills and drops.
- POCKET-SIZED – fits easily in pockets and small bags.
- SPACE TO OWN YOUR AI CONTENT – speed and capacity to download your high-res clips and photo edits.
- 256-BIT AES ENCRYPTION(4) – helps keep private files secure with password protection.
Keep models and move their storage instead
If you want to retain your models but need room on the internal drive, configure a different destination before downloading more. Ollama supports an alternate model directory through OLLAMA_MODELS, and Hugging Face supports an alternate cache directory through HF_HUB_CACHE or HF_HOME. See the Ollama FAQ and Hugging Face Hub CLI guide. An external SSD can serve as the destination, but plugging in a drive does not move existing downloads: configure the app or cache path and handle the existing copies separately, then verify the new location is being used.
Check the result
After removing cache data, use the cleanup output and your system’s available disk space to check the change. For other applications, compare the model inventory or operating-system storage reading before and after. Do not assume the amount reclaimed from a model’s displayed size: shared files, cache references, and custom locations can affect the result.
Quick Recap
Best Value
- Easily store and access 2TB to content on the go with the Seagate Portable Drive, a USB external hard drive
- Designed to work with Windows or Mac computers, this external hard drive makes backup a snap just drag and drop
- To get set up, connect the portable hard drive to a computer for automatic recognition no software required
- This USB drive provides plug and play simplicity with the included 18 inch USB 3.0 cable
- The available storage capacity may vary.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
