News for hackers. Stuff that matters.

A comment on Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses. Parent comment

Re:Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1... by SwellJoe on Tuesday September 08, 2026 @12:08PM (#49612349)
Even at 30 t/s, 3.8 thinks so long, even on medium, it still takes 3x or more longer than any cloud model, in my testing.
[ Parent | on HN ]
Re:Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1... by lowbloodsugar on Tuesday September 08, 2026 @01:52PM (#49613962)
I've got an M1 Max 64GB too. It's just not an LLM-class workstation. Give it a year and buy an M7 and you'll be laughing. Right now is a really bad time to invest in anything - using the cloud is the cheapest option, especially for open weight models.
[ Parent | on HN ]