Loading video player...
š Access ALL video resources & get personalized help in my community: https://www.skool.com/agentic-labs š¦ Download Ollama: https://ollama.com š¬ My AI voice-to-text software (Wispr Flow): https://wisprflow.ai/r?LEON114 ā Buy me a coffee: https://www.buymeacoffee.com/leonvanzyl šµ Donate using PayPal: https://www.paypal.com/ncp/payment/EKRQ8QSGV6CWW In this video you will learn how to use local models in Claude Code completely free using Ollama. Run AI coding agents offline on your own machine with no API costs or subscriptions. You will learn how to install Ollama, download recommended models like Qwen3-Coder, GPT-OSS, and GLM 4.7 Flash, and configure Claude Code to use local LLMs. Perfect for vibe coding and agentic coding on consumer grade hardware with full access to Claude Code features like subagents, MCP servers, and slash commands. ā° TIMESTAMPS: 00:00 Claude Code local models demo 01:05 Install Ollama on your machine 01:47 Download models from Ollama 02:15 Recommended models for Claude Code 02:30 GPT OSS 20B VRAM requirements 02:42 Qwen3 Coder best local coding model 02:49 GLM 4.7 Flash model overview 05:30 Configure Claude Code with Ollama 06:06 Test offline mode no API key 06:36 Local models vs Sonnet and Opus 07:10 Troubleshooting Ollama errors 08:01 Context window size comparison #claudecode #vibecoding #agenticcoding