Ode to Qwen 3.8 Flash Next

(terra-incognita.blog)

4 points | by incognito124 a day ago ago

3 comments

  • d3Xt3r a day ago

    One improvement the author could've made is to switch from llama.cpp to a more optimised inference engine like Strata. 60 tok/s is on the lower end for an A6000, with Strata I'd expect upwards of 90 tok/s.

    • incognito124 a day ago

      I'm the author: thanks, I'll look into it, I didn't yet heae about it!

  • speedupagi 18 hours ago

    [flagged]