Inference › Optimization & Performance › Context / KV Cache v
draft model choices on mini PC

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
draft model choices on mini PC
cacheline Offline
Senior Member
****
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation: 0
#11
09-10-2026, 03:43 PM
Quote:I'd approach it in a boring order. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious.

following this because I'm in the same boat.
measure twice, benchmark three times
Find
Reply


Messages In This Thread
draft model choices on mini PC - by cacheline - 09-05-2026, 10:52 PM
Re: draft model choices on mini PC - by cacheline - 09-06-2026, 01:20 AM
Re: draft model choices on mini PC - by cacheline - 09-06-2026, 10:12 AM
Re: draft model choices on mini PC - by cacheline - 09-09-2026, 11:13 AM
Re: draft model choices on mini PC - by cacheline - 09-09-2026, 01:20 PM
Re: draft model choices on mini PC - by cudaline - 09-09-2026, 01:41 PM
Re: draft model choices on mini PC - by cacheline - 09-10-2026, 02:11 PM
Re: draft model choices on mini PC - by phaseshed - 09-10-2026, 03:05 PM
Re: draft model choices on mini PC - by cacheline - 09-10-2026, 03:43 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)