vbtechguy3d ago

Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code

https://ai.georgeliu.com/p/running-google-gemma-4-locally-with

Running Google Gemma 4 Locally With LM Studio’s New Headless CLI & Claude Code

LM Studio 0.4.0 introduced llmster and the lms CLI. Here is how I set up Gemma 4 26B for local inference on macOS that can be used with Claude Code.

George Liu
Show threadtrvz

ollama launch claude --model gemma4:26b

Apr 5 at 7:11pmWeb
Show threaddatadrivenangel3d ago
It's amazing how simple this is, and it just works if you have ollama and claude installed!
Show threadpshirshov3d ago
For some reason, that doesn't work for me, claude never returns from some ill loop. Nemotron, glm and qwen 3.5 work just fine, gemma - doesn't.
Show threadtrvz3d ago

Since that defaults to the q4 variant, try the q8 one:

ollama launch claude --model gemma4:26b-a4b-it-q8_0