Ollama makes it easy to download local AI models, which is exactly why your C: drive can fill up without you noticing. Each model is a large file, and Ollama's own Windows documentation warns that models "can be tens to hundreds of GB in size". This guide covers the handful of commands you need to keep your model library under control, and how to move it to a bigger drive.
Forge PC hasn't benchmarked anything for this guide. The steps follow Ollama's official CLI reference, FAQ and Windows documentation, checked on 17 November 2026. Commands can change between Ollama versions, so if one doesn't work, check Ollama's CLI reference for your version. New to Ollama? Start with our guide to running AI models locally with Ollama and LM Studio.
Step 1: See which models you have
Open Terminal or PowerShell and run:
ollama ls
Ollama's CLI reference lists ollama ls as the command to list models. It shows each model's name and tag, so you can spot duplicates, such as two sizes of the same model, that you no longer need.
Step 2: Check what's loaded right now
ollama ps
This lists running models, meaning those currently loaded into memory. To unload one and free up VRAM or system RAM without deleting it, use ollama stop followed by the model name, for example ollama stop gemma4.
Step 3: Delete models you don't use
ollama rm gemma4
Replace gemma4 with the exact name and tag shown by ollama ls. This deletes the model from disk. You can download it again later with ollama pull, but on a slow connection that can take a while for large models, so only delete what you're sure you won't need.
Not sure which sizes are worth keeping? Our guides to quantisation and GGUF files and the best local LLM models help you decide which versions suit your graphics card.
Step 4: Find where models are stored
According to Ollama's FAQ, models are stored by default at:
Platform | Default model folder |
|---|
Windows | C:\Users\%username%.ollama\models |
Linux | /usr/share/ollama/.ollama/models |
macOS | ~/.ollama/models |
On Windows you can open the folder that holds models and configuration by pressing Windows + R and entering explorer %HOMEPATH%\.ollama.
Step 5: Move models to another drive on Windows 11
Ollama uses an environment variable called OLLAMA_MODELS to decide where models live. Ollama's Windows documentation gives these steps:
Quit Ollama from its icon in the taskbar.
Open Settings and search for environment variables.
Select Edit environment variables for your account.
Create a new variable named OLLAMA_MODELS and set its value to the folder you want, for example D:\OllamaModels.
Select OK to save.
Start Ollama again from the Start menu, or from a new terminal opened after you saved the variable.
Ollama's documentation doesn't describe moving existing downloads. The simplest route is to set the new folder, then re-download the models you want with ollama pull. If you'd rather copy your existing models folder across before restarting Ollama, keep the original until you've confirmed with ollama ls that everything shows up.
On Linux with the standard installer, the FAQ says the ollama user needs read and write access to the new folder, which you can grant with sudo chown -R ollama:ollama <directory>.
If you need a bigger drive for models, our how to install an M.2 SSD guide and best 2TB SSD picks can help if you need more space.
Uninstalling Ollama
If you uninstall Ollama through Add or remove programs, its Windows documentation notes that the installer won't remove your downloaded models if you changed the OLLAMA_MODELS location. Delete that folder yourself if you want the space back.
Our verdict
Use ollama ls to see your models, ollama ps to see what's loaded, ollama stop to unload a model and ollama rm to delete one. On Windows 11, models live in C:\Users\%username%.ollama\models by default; to move them, quit Ollama, set an OLLAMA_MODELS user environment variable to a folder on a bigger drive and restart it. Uninstalling won't remove models stored in a custom folder. Forge PC hasn't benchmarked anything for this guide.