Running ChatGPT on a Raspberry Pi with Ryan Reynolds
Discover how a large language model performs on a credit card-sized Raspberry Pi. Is it smarter than a potato? Unveil nerd history today!
File
ChatGPT Running Locally on Raspberry Pi (ft. Ryan Reynolds)
Added on 01/29/2025
Speakers
add Add new speaker

Speaker 1: Today, Ryan Reynolds and I are going to unveil the world's smallest instance of ChatGPT. I know, usually bigger means better, but I'm poor, so I'm going to go in the other direction and make nerd history by running a large language model on a Raspberry Pi, which is a single-board computer about the size of a credit card. First, I'm going to flash the Ubuntu operating system to my Raspberry Pi, because frankly, I don't think Raspberry Pi OS is up for the challenge. Next, I'll download the llama.cpp git repo. I totally understand this code. Next, we'll compile the code and start the chatbot. But is the model any smarter than a potato? Let's find out. So to gauge its intelligence level, I posed an age-old question. Why did the chicken cross the road? This thing is writing a TED talk right now. Initially, the answer appears simple. The chicken wanted to get to the other side.

Speaker 2: But as I delve deeper into this query, the more it reveals the broader complacency of humans. And we create a new layout. And turn it off.

Speaker 1: Shut it down. I'm having fun.

ai AI Insights
Summary

Generate a brief summary highlighting the main points of the transcript.

Generate
Title

Generate a concise and relevant title for the transcript based on the main themes and content discussed.

Generate
Keywords

Identify and highlight the key words or phrases most relevant to the content of the transcript.

Generate
Enter your query
Sentiments

Analyze the emotional tone of the transcript to determine whether the sentiment is positive, negative, or neutral.

Generate
Quizzes

Create interactive quizzes based on the content of the transcript to test comprehension or engage users.

Generate
{{ secondsToHumanTime(time) }}
Back
Forward
{{ Math.round(speed * 100) / 100 }}x
{{ secondsToHumanTime(duration) }}
close
New speaker
Add speaker
close
Edit speaker
Save changes
close
Share Transcript