Inference › Drivers / Frameworks / Toolkits › Apple / MLX v
M3 Max for local use on 4090

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
M3 Max for local use on 4090
turboyard94 Offline
Member
***
Posts: 54
Threads: 7
Joined: Sep 2026
Reputation: 0
#1
09-27-2026, 06:07 PM
Thought I'd post a small recipe because a lot of threads ask similar things.

Maybe useful as a starting point: PyTorch on Threadripper box, keeping small local stacks in mind from the start.

Maybe useful as a starting point for newer folks.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
Find
Reply


Messages In This Thread
M3 Max for local use on 4090 - by turboyard94 - 09-27-2026, 06:07 PM
Re: M3 Max for local use on 4090 - by turboyard94 - 09-29-2026, 06:43 AM
Re: M3 Max for local use on 4090 - by mlxgarden - 09-30-2026, 07:05 AM
Re: M3 Max for local use on 4090 - by mlxgarden - 10-03-2026, 10:25 PM
Re: M3 Max for local use on 4090 - by quietarch - 10-08-2026, 07:57 AM
Re: M3 Max for local use on 4090 - by amberplane - 10-04-2026, 06:45 AM
Re: M3 Max for local use on 4090 - by turboyard94 - 10-04-2026, 07:02 PM
Re: M3 Max for local use on 4090 - by mlxgarden - 10-05-2026, 07:36 AM
Re: M3 Max for local use on 4090 - by mlxgarden - 10-08-2026, 08:18 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)