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
cudacrate Offline
Junior Member
**
Posts: 47
Threads: 4
Joined: Aug 2026
Reputation: 0
#9
10-18-2026, 04:00 PM
Thanks, that helps. The pattern around speculative decoding has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
learning in public
Find
Reply


Messages In This Thread
M3 Max for local use - by byteyard - 10-16-2026, 07:42 AM
Re: M3 Max for local use - by mlxgarden - 10-17-2026, 08:25 PM
Re: M3 Max for local use - by labnest - 10-17-2026, 10:40 PM
Re: M3 Max for local use - by rasterbench - 10-18-2026, 11:12 AM
Re: M3 Max for local use - by mlxgarden - 10-18-2026, 11:49 AM
Re: M3 Max for local use - by thetaarch43 - 10-18-2026, 01:00 PM
Re: M3 Max for local use - by plainember52 - 10-18-2026, 03:15 PM
Re: M3 Max for local use - by quietarch - 10-18-2026, 03:51 PM
Re: M3 Max for local use - by cudacrate - 10-18-2026, 04:00 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)