Running local models on an M4 with 24GB memory

Re:Running local models on an M4 with 24GB memory by sbassi on Sunday May 10, 2026 @07:33PM (#48089245)

A useful data to know about this setup is how many tokens/sec generates.

[ Parent | on HN ]

Re:Running local models on an M4 with 24GB memory by JBorrow on Sunday May 10, 2026 @07:40PM (#48089298)

It’s started in TFA

[ Parent | on HN ]

Re:Running local models on an M4 with 24GB memory by NDlurker on Sunday May 10, 2026 @07:50PM (#48089368)

You can't expect someone to read 4 paragraphs into an article before commenting

[ Parent | on HN ]

Re:Running local models on an M4 with 24GB memory by kennywinker on Sunday May 10, 2026 @08:00PM (#48089445)

@grok is this true?

[ Parent | on HN ]

Re:Running local models on an M4 with 24GB memory by DrBenCarson on Sunday May 10, 2026 @08:10PM (#48089527)

Sorry, @grok is offline after declaring himself MechaMussolini earlier today

[ Parent | on HN ]