Unplug the Internet: Free AI Coding with Ollama
Read the Portuguese translation →
Author: Leon van Zyl · Watch on YouTube
Video authored by the channel shown, not by IANIA; all rights belong to the creator. Transcript and summary generated automatically; the original-language content is preserved.
Original language: English
Original video: Unplug the Internet: Free AI Coding with Ollama · Channel: Leon van Zyl · 00:34 · Watch on YouTube
Topics: AI agents, Software engineering with AI, Local and open-source models
Summary
Section titled “Summary”The video explains that running an AI model locally keeps it secure and usable offline, even with the network disconnected. It recommends using Ollama to run local models and mentions Code 3.8 as a good option for coding tasks. The speaker advises asking a coding agent to check your hardware and recommend a model you can realistically run. The video then demonstrates starting a model download with ollama pull and using a local model in Open Code.
Key points
Section titled “Key points”- Local models can run securely and offline.
- Disconnecting from the network does not stop the local setup from working.
- Ollama is presented as an easy way to run models locally.
- The speaker recommends Code 3.8 for coding tasks.
- Ask a coding agent to assess your hardware and suggest a suitable model.
- Use
ollama pullfollowed by the model name to download a model. - The speaker runs a local model in Open Code.
Chapters
Section titled “Chapters”| Start | Chapter | Summary |
|---|---|---|
| 00:00 | Benefits of running a model locally | The speaker describes the security and offline benefits of running a local model. |
| 00:00 | Choosing a model for coding | The speaker recommends Code 3.8 and suggests matching the model to your hardware. |
| 00:34 | Downloading and running the model | The speaker describes using ollama pull and notes that a local model is running in Open Code. |
Quotes
Section titled “Quotes”it is secure, it’s offline. — 00:00
everything will continue working. — 00:00
This is a really good model, especially for coding tasks. — 00:00
I’m actually running a local model on my machine in open code. — 00:34
Concepts and entities
Section titled “Concepts and entities”Ollama, Code 3.8, OpenCode, modelos locais
Full transcript (original language)
Section titled “Full transcript (original language)”00:00 And the benefit of running this model locally is it is secure, it’s offline. I can actually disconnect from the network entirely and everything will continue working. One of the easiest ways to run local models on your machine is to use something like a llama. Personally, I like to run code 3.8. This is a really good model, especially for coding tasks. One piece of advice I will give you is ask your coding agent or coder or whatever you’re using to look at your hardware and recommend a model on a llama that you could realistically run. Back in the terminal, we can run a llama pull and then we’ll paste in the name of
00:34 the model. Now, I’m actually running a local model on my machine in open code.