News for hackers. Stuff that matters.

A comment on GLM5 Released on Z.ai Platform. Parent comment

Re:GLM5 Released on Z.ai Platform by nialv7 on Wednesday February 11, 2026 @09:54AM (#46975705)
> Didn't expect to go back to macOS but their basically the only feasible consumer option for running large models locally.

Framework Desktop! Half the memory bandwidth of M4 Max, but much cheaper.

[ Parent | on HN ]
Re:GLM5 Released on Z.ai Platform by thebruce87m on Wednesday February 11, 2026 @10:38AM (#46976285)
Does that equate to half the speed in terms of output? Any recommended benchmarks to look at?
[ Parent | on HN ]
Re:GLM5 Released on Z.ai Platform by nialv7 on Wednesday February 11, 2026 @10:57AM (#46976534)
https://kyuz0.github.io/amd-strix-halo-toolboxes/
[ Parent | on HN ]