Move Ollama Models to different location

Ollama LLM model files take a lot of space

Page content

After installing ollama better to reconfigure ollama to store them in new place right away. So after we pull a new model, it doesn’t get downloaded to the old location.

Smart llama in the hat is doing something in the server room

About Ollama

Ollama is a text-based frontend to LLM AI Models and an API that can host those too.

Install Ollama

Goto https://ollama.com/download

To install Ollama on linux:

curl -fsSL https://ollama.com/install.sh | sh

Ollama on Windows is on page: https://ollama.com/download/windows Ollama for Mac is there too: https://ollama.com/download/macOllamaSetup.exe

Download, List and Remove Ollama models

To download some Ollama models: Go to Ollama Library (https://ollama.com/library) and find the model you need, there you can also find model tags and sizes.

Then run:

ollama pull gemma2:latest

# Or get slightly smarter one still nicely fitting into 16GB VRAM:
ollama pull gemma2:27b-instruct-q3_K_S

# Or: 
ollama pull llama3.1:latest
ollama pull llama3.1:8b-instruct-q8_0
ollama pull mistral-nemo:12b-instruct-2407-q6_K
ollama pull mistral-small:22b-instruct-2409-q4_0
ollama pull phi3:14b-medium-128k-instruct-q6_K
ollama pull qwen2.5:14b-instruct-q5_0

To check the models Ollama has in local repository:

ollama list

To remove some unneeded model:

ollama rm qwen2:7b-instruct-q8_0 # for example

Ollama Model location

By default the model files are stored:

  • Windows: C:\Users%username%.ollama\models
  • Linux: /usr/share/ollama/.ollama/models
  • macOS: ~/.ollama/models

Configuring Ollama models path on Windows

To create an environment variable on Windows you can follow these instructions:

  • Open Windows Settings.
  • Go to System.
  • Select About
  • Select Advanced System Settings.
  • Go to the Advanced tab.
  • Select Environment Variables….
  • Click on New…
  • And create a variable called OLLAMA_MODELS pointing to where you want to store the models

Move Ollama models on Linux

Edit the ollama systemd service parameters

sudo systemctl edit ollama.service

or

sudo xed /etc/systemd/system/ollama.service

This will open an editor.

For each environment variable, add a line Environment under section [Service]:

[Service]
Environment="OLLAMA_MODELS=/specialplace/ollama/models"

Save and exit.

There is also a User and Group params, those must have access to this folder.

Reload systemd and restart Ollama:

sudo systemctl daemon-reload
sudo systemctl restart ollama

if something went wrong

systemctl status ollama.service
sudo journalctl -u ollama.service

Storing files on NTFS overhead

Please be aware that if you are running linux and keeping your models on NTFS formatted partition, your models would be loading much - more then 20% slower.

ntfs.mount cpu usage

Install Ollama on Windows to specific folder

Together with the models

.\OllamaSetup.exe /DIR=D:\OllamaDir

Expose Ollama API to internal network

Internal here means local network.

Add to service config:

[Service]
Environment="OLLAMA_HOST=0.0.0.0"