1.1 – Linux<\/p>\n\n\n\n
On Debian linux, Installing Ollama is a one liner, just enter the following in your terminal<\/p>\n\n\n\n
curl -fsSL https:\/\/ollama.com\/install.sh | sh<\/pre>\n\n\n\nYup, that is it, move on to using Ollama<\/p>\n\n\n\n
1.2 Windows and MAC<\/p>\n\n\n\n
Just go to https:\/\/ollama.com\/<\/a>, download it, and run the installer ! you are done<\/p>\n\n\n\n
Optional: Changing the models directory<\/strong><\/h2>\n\n\n\n
AI models can be very big, sometimes half a terabyte, for example, at the time of writing, deepseek model was around 700GBs, but the disk you are copying to needs to be an SSD if you want reasonable speed.<\/p>\n\n\n\n
So here are the steps<\/p>\n\n\n\n
\n
sudo systemctl stop ollama<\/code><\/li>\n\n\n\nsudo mkdir -p \/hds\/2tb\/ollama_models<\/code> (Wherever you want the data to be)<\/li>\n\n\n\nsudo chown ollama:ollama \/hds\/2tb\/ollama_models<\/code> (Whatever your username is)<\/li>\n\n\n\nsudo mkdir -p \/etc\/systemd\/system\/ollama.service.d\/<\/code> (This is the override conf)<\/li>\n\n\n\nsudo nano \/etc\/systemd\/system\/ollama.service.d\/override.conf<\/code>
and add the following to it
[Service]
Environment=”OLLAMA_MODELS=\/hds\/2tb\/ollama_models”<\/li>\n\n\n\nsudo systemctl daemon-reload<\/code><\/li>\n\n\n\nsudo systemctl start ollama<\/code><\/li>\n\n\n\nsudo systemctl show -p Environment ollama<\/code><\/li>\n<\/ul>\n\n\n\nUsing it !<\/h3>\n\n\n\n
Using Ollama is simple, just open your terminal window or command prompt , then activate your conda environment (Or venv) , and run the following command, for the sake of this example, I will run<\/p>\n\n\n\n
ollama run llama3.2<\/pre>\n\n\n\nllama3.3<\/strong> with its 70 billion parameters will require a minimum of 64GB of ram, so don’t try that unless you have the RAM for it ! for comparison, 3.2 has 2 billion, which is around 3% of 3.3<\/p>\n\n\n\n
It should now probably download about 2GBs of data (The model llama3.2 has around 2 billion parameters) And you are done, Now you can ask it anything<\/p>\n\n\n\n
For example, create an article for me explaining this and that, <\/p>\n\n\n\n
Once done, just enter “\/bye” to exit the ollama prompt and quit the session<\/p>\n\n\n\n
If you want to for example clear the context or do anything else, just use the command \/? for a list of commands<\/p>\n\n\n\n
Now, you have used the lama3.2, but on this ollama models page<\/a>, you will find that there are many others that you can use !<\/p>\n\n\n\n
Others include models that help you with coding, or models that are more targeted towards chat-bot QA, either way, you should take a close look at them, even if for the fun of it<\/p>\n\n\n\n
Is ollama running ?<\/h2>\n\n\n\n