Simon P. Couch @simonpcouch.com · Jan 26

ollama recently implemented support for Anthropic’s Messages API, meaning that you can hook up Claude Code to an LLM running on your laptop. This is really neat, but I’ve seen some posts about how you can now have “Claude Code for $0.” A word of caution: www.simonpcouch.com/blog/2025-12...

13 likes 4 replies

?

Replies

Alex Vero · Mar 13

Important caveat that people miss. Local models through Ollama are great for experimentation and privacy, but the gap in code quality between a local 7B and Claude Sonnet is massive. You get the CLI for $0 but not the intelligence that makes it useful.

Hadley Wickham · Jan 26

Brutal

Theodore Alysandratos · Jan 26

For those who don't like ollama, llama.cpp has also implemented the messages API huggingface.co/blog/ggml-or...

Jordi Rosell · Jan 26

Wow. Only Claude Code. Even Gemini Pro 2.5 can't get 100%. What about their speed? And Gemini Pro 3?