← Zurück zur Videothek

Claude Code + Ollama = FULL LOCAL AI AGENT

Prompt Engineer · 2026-04-26 · 🇬🇧 Englisch · YouTube Playlist
https://www.youtube.com/watch?v=7kNz_6hKHVs
▶ Video auf YouTube

📄 Zusammenfassung

So, what I can do is you can download some other models on your local system and then you can just say Ollama launch Claude and then you can just put in the name of the new model. So, I'm going to stop this, but let's go ahead and do Ollama list and you can see that I already have installed Ollama and I can see all these models that I have. And if I go back and and I say Ollama pull and the name of the model here, if you do this, it's going to pull the model from the Ollama storage and you can see that 6.6GB and it's a success. So, we can see slash models model and you can see that all these models, so custom Sonnet model, custom Opus model, custom HiQ and all these four models, basically there are three models and this is a custom model. So, you can see that Ollama PS Quen 3.5 9 billion is running, which is a size of 9.8GB and you can see that CPU, 45% of my CPU and 55% of my GPU is being used to run this model.

📚 Kapitel

00:00
Intro – Why Use Local AI Instead of Claude Paid Plans
01:01
Project Setup (VS Code + Terminal)
01:30
Install Claude Code
02:05
Choose Best Local Model (Qwen 3.5)
02:27
Install Ollama (Fix Environment Variables)
03:53
Verify Ollama Installation
04:22
Download & Setup Qwen Model
05:35
Test Local Model (Basic Prompt)
06:05
Run Claude Code with Local Model
07:13
Check CPU/GPU Usage (Performance)
08:01
Context Length Problem Explained
08:17
Increase Context Size (Modelfile)
09:19
Create 64K Context Model
10:03
Run Claude with Bigger Context
10:24
Real Demo – Clone GitHub Repo
11:38
Other Models (Cloud / RunPod Options)
12:40
Analyze Output & Requirements
13:29
Final Thoughts (Limits & Notes)
13:42
Outro + Next Video (OpenRouter)

📺 Ähnliche Videos