Inference › Drivers / Frameworks / Toolkits › Apple / MLX v
M3 Max for local use

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
M3 Max for local use
sanescope Offline
Junior Member
**
Posts: 48
Threads: 5
Joined: Sep 2026
Reputation: 0
#9
09-20-2026, 11:56 AM
Quote:Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than

Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?
Find
Reply


Messages In This Thread
M3 Max for local use - by labnest - 09-17-2026, 11:13 PM
Re: M3 Max for local use - by dockridge - 09-18-2026, 03:37 AM
Re: M3 Max for local use - by thetaarch43 - 09-18-2026, 04:32 AM
Re: M3 Max for local use - by pixelcrate82 - 09-18-2026, 04:52 PM
Re: M3 Max for local use - by amberhall - 09-18-2026, 09:14 PM
Re: M3 Max for local use - by cudacrate - 09-18-2026, 10:15 PM
Re: M3 Max for local use - by circuitwire58 - 09-18-2026, 11:11 PM
Re: M3 Max for local use - by turboyard94 - 09-18-2026, 11:41 PM
Re: M3 Max for local use - by sanescope - 09-20-2026, 11:56 AM
Re: M3 Max for local use - by sanescope - 09-20-2026, 03:11 PM
Re: M3 Max for local use - by deepseeked - 09-20-2026, 12:29 PM
Re: M3 Max for local use - by thetaarch43 - 09-20-2026, 01:28 PM
Re: M3 Max for local use - by pixelcrate82 - 09-20-2026, 03:25 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)