Claude Code: connect to a local model when your quota runs out

Re:Claude Code: connect to a local model when your quota run... by BuildTheRobots on Thursday February 05, 2026 @03:12AM (#46897051)

I don't suppose you could point to any resources on where I could get started. I have a M2 with 64gb of unified memory and it'd be nice to make it work rather than burning Github credits.

[ Parent | on HN ]

Re:Claude Code: connect to a local model when your quota run... by EagnaIonat on Thursday February 05, 2026 @03:36AM (#46897226)

https://ollama.com

Although I'm starting to like LMStudio more, as it has more features that Ollama is missing.

https://lmstudio.ai

You can then get Claude to create the MCP server to talk to either. Then a CLAUDE.md that tells it to read the models you have downloaded, determine their use and when to offload. Claude will make all that for you as well.

[ Parent | on HN ]

Re:Claude Code: connect to a local model when your quota run... by shen on Thursday February 05, 2026 @11:39AM (#46901516)

Which local models are you using for the 32gb MacBooks?

[ Parent | on HN ]

Re:Claude Code: connect to a local model when your quota run... by EagnaIonat on Thursday February 05, 2026 @11:23PM (#46909094)

Mainly gpt-oss-20b as the thinking mode is really good. I occasionally use granite4 as it is a very fast model. But any 4GB model should easily be used.

[ Parent | on HN ]

Re:Claude Code: connect to a local model when your quota run... by eek2121 on Thursday February 05, 2026 @10:58AM (#46901063)

LM Studio is fantastic for playing with local models.

[ Parent | on HN ]