Loading video player...
Get my Favourite GPUs 👉🏻: https://get.runpod.io/pe48 In this video, I show how to replace expensive Claude models with local models running on your own machine — and still use Claude Code like a pro. Instead of relying on paid models like Opus, Sonnet, or Haiku, we plug in lightweight local models using Ollama and make Claude Code work seamlessly with them. 💡 What you’ll learn: • How Claude Code normally uses paid models • How to swap them with local Ollama models • Running everything fully on your system • Building a completely free AI coding workflow ⚡ Why this is powerful: • 💰 Zero API costs • 🔒 100% private (everything runs locally) 🛠️ Tech Stack: • Ollama (local model runtime) • Lightweight Models: we used Qwen3.5:9b • Claude Code setup • VS Code + extensions Links: https://docs.ollama.com/integrations/claude-code https://docs.ollama.com/modelfile 🔥 Perfect for: • Developers who want a private AI assistant • Anyone tired of paying for APIs • Local-first AI workflows • Open-source AI enthusiasts 🔗 My Links ☕ Support me https://ko-fi.com/promptengineer 📱 Patreon https://www.patreon.com/PromptEngineer975 📞 Book a Call https://calendly.com/prompt-engineer48/call 📔Github: https://github.com/PromptEngineer48 Tags: #ClaudeCode, #Ollama, #LocalAI, #OfflineAI, #AIagent, #AICoding, #AIDeveloper, #OpenSourceAI, #SelfHostedAI, #NoAPICost, #PrivateAI, Timestamp: 0:00 Intro – Why Use Local AI Instead of Claude Paid Plans 1:01 Project Setup (VS Code + Terminal) 1:30 Install Claude Code 2:05 Choose Best Local Model (Qwen 3.5) 2:27 Install Ollama (Fix Environment Variables) 3:53 Verify Ollama Installation 4:22 Download & Setup Qwen Model 5:35 Test Local Model (Basic Prompt) 6:05 Run Claude Code with Local Model 7:13 Check CPU/GPU Usage (Performance) 8:01 Context Length Problem Explained 8:17 Increase Context Size (Modelfile) 9:19 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)