Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
1–10 of 121 posts
Re: Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
#2Here is how I set up Gemma 4 26B for local inference on macOS that can be used with Claude Code.
Re: Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
#3Here is how I set up Gemma 4 26B for local inference on macOS that can be used with Claude Code.
This is a nice writeup!
Re: Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
#4 ollama launch claude --model gemma4:26bRe: Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
#5So wait what is the interaction between Gemma and Claude?
Re: Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
#6So wait what is the interaction between Gemma and Claude?
lm studio offers an Anthropic compatible local endpoint, so you can point Claude code at it and it'll use your local model for it's requests, however, I've had a lot of problems with LM Studio and Claude code losing it's place. It'll think for awhile, come up with a plan, start to do it and then just halt in the middle. I'll ask it to continue and it'll do a small change and get stuck again.
Using ollama's api doesn't have the same issue, so I've stuck to using ollama for local development work.
Re: Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
#7Using Claude Code seems like a popular frontend currently, I wonder how long until Anthropic releases an update to make it a little to a lot less turn-key? They've been very clear that they aren't exactly champions of this stuff being used outside of very specific ways.
Re: Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
#8ollama launch claude --model gemma4:26b
It's amazing how simple this is, and it just works if you have ollama and claude installed!
Re: Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
#9So wait what is the interaction between Gemma and Claude?
lm studio offers an Anthropic compatible local endpoint, so you can point Claude code at it and it'll use your local model for it's requests, however, I've had a lot of problems with LM Studio and Claude code losing it's place. It'll think for awhile, come up with a plan, start to do it and then just halt in the middle. I'll ask it to continue and it'll do a small change and get stuck again. Using ollama's api doesn'…
Claude Code is fairly notoriously token inefficient as far as coding agent/harnesses go (i come from aider pre-CC). It's only viable because the Max subscriptions give you approximately unlimited token budget, which resets in a few hours even if you hit the limit. But this also only works because cloud models have massive token windows (1M tokens on opus right now) which is a bit difficult to make happen locally with the VRAM needed.
And if you somehow managed to open up a big enough VRAM playground, the open weights models are not quite as good at wrangling such large context windows (even opus is hardly capable) without basically getting confused about what they were doing before they finish parsing it.
Re: Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
#10Using Claude Code seems like a popular frontend currently, I wonder how long until Anthropic releases an update to make it a little to a lot less turn-key? They've been very clear that they aren't exactly champions of this stuff being used outside of very specific ways.
Right now it suits them down to the ground. You pay for the product and you don’t cost their servers anything.