Nemotron-Mini, developed by NVIDIA, is a small language model optimized for roleplay, retrieval-augmented generation (RAG) QA, and function calling. It offers a lightweight solution suitable for on-device deployment, making it efficient and versatile for a range of applications.
Prerequisites: Ensure you have Ollama installed on your system. Python should also be installed and verified.
Step 1: Verify Environment Setup
- Open Terminal and check Ollama’s installation:
ollama --version
Step 2: Install Nemotron-Mini
- Pull the Nemotron-Mini model using the command:
ollama run nemotron-mini- The model size is 2.7 GB, so ensure you have sufficient storage and a stable internet connection.
Step 3: Test the Installation
- Run the following to test the model:
ollama run nemotron-mini- Enter a prompt, such as:
What is 25 × 4 − 10?- Ensure Nemotron-Mini responds correctly.
Step 4: Troubleshooting
- Internet Connection: Ensure stability when pulling models.
- Storage Availability: Make sure your system has enough space.
By following these steps, you can successfully set up Nemotron-Mini on your Mac M1, M2, or M3.