Replacing Claude Code’s AI Model with Ollama on Jetson

Join this channel to get access to perks:
https://www.youtube.com/channel/UCQs0lwV6E4p7LQaGJ6fgy5Q/join

Install Ollama and Claude Code on NVIDIA Jetson, then use Ollama as the inference server for both local and cloud AI models. This video walks through setup on Jetson Orin Nano, tests Nemotron 3 Nano locally, explains why context size matters for Claude Code, and compares local inference with Ollama Cloud models.

We also move to Jetson AGX Thor to test larger models, including Nemotron 3 Nano 30B and Gemma 4, while comparing startup time, tool use, responsiveness, and whether each model can complete real coding-agent tasks. The goal is not just to make Claude Code run with another model, but to see when local or lower-cost models are actually useful.

Links:
Jetson Tools: https://github.com/jetsonhacks/jetson-tools/
Jetson Tools - Install Ollama: https://github.com/jetsonhacks/jetson-tools/blob/main/tools/install-ollama-jetson.sh
Ollama: https://ollama.com
Claude: https://claude.ai/
jetson-device-skills: https://github.com/NVIDIA-AI-IOT/jetson-device-skills


Chapters:
00:00 Introduction
01:04 Install Ollama
03:10 Test Nemotron 3 Nano
06:32 Install and Run Claude Code with Ollama
07:48 Compare with Claude Code using Sonnet
09:52 Running Claude Code locally on AGX Thor




As an Amazon Associate I earn from qualifying purchases.
Visit the JetsonHacks storefront on Amazon: https://www.amazon.com/shop/jetsonhacks

Visit the website at https://jetsonhacks.com
Sign up for the newsletter! https://newsletter.jetsonhacks.com
Github accounts: https://github.com/jetsonhacks
https://github.com/jetsonhacksnano
Twitter: http://twitter.com/jetsonhacks

Some of these links here are affiliate links. As an Amazon Associate I earn from qualifying purchases at no extra cost to you.