In this video, I look at using Claude Code with Ollama's new function called Ollama Launch along with the GLM 4.7 Flash model. 

Blog: https://ollama.com/blog/launch
HF: https://huggingface.co/zai-org/GLM-4.7-Flash
Ollama Claude API:  https://ollama.com/blog/claude

For more tutorials on using LLMs and building agents, check out my Patreon
Patreon: https://www.patreon.com/SamWitteveen
Twitter: https://x.com/Sam_Witteveen 

🕵️ Interested in building LLM Agents? Fill out the form below
Building LLM Agents Form: https://drp.li/dIMes

👨‍💻Github:
https://github.com/samwit/llm-tutorials

Sam Witteveen AI is a publication offering insights, tutorials, and resources for artificial intelligence (AI) enthusiasts and practitioners. Readers can learn about machine learning algorithms, deep learning frameworks, and AI applications. With tutorials, case studies, and expert interviews, Sam Witteveen AI provides  guidance and expertise for building and deploying AI solutions.

Sam Witteveen

Ollama has launched a new feature called Ollama Launch that enables running Claude Code and other AI coding assistants locally using the Anthropic API. The author tests the GLM 4.7 Flash model (30B parameters with 3B active) on a Mac Mini Pro with 32GB RAM. While the setup is straightforward—requiring only updating Ollama, pulling the model, and adjusting the context length to 64K—performance is significantly slower than cloud-based Claude Code. The model struggles with tool arguments and requires powerful hardware to run efficiently. The author concludes that while promising for future local AI agents, current local models aren't yet viable replacements for cloud-based Claude Code unless you have high-end hardware.

Ollama Launch + Claude Code + GLM Flash