Inference › Inference Engines › Other Engines v
tokens/sec tuning ideas

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
tokens/sec tuning ideas
mlxgarden Offline
Member
***
Posts: 199
Threads: 27
Joined: Sep 2026
Reputation: 0
#1
10-12-2026, 06:36 PM
Spent some time on this today and wanted to compare notes.

I'm comparing two approaches here: keep it simple on B200, or squeeze more out of the stack and deal with the complexity.

Interested in tradeoffs more than fan loyalty. The logs were somehow calmer than I was.
M3 Max • MLX • local-first
Find
Reply


Messages In This Thread
tokens/sec tuning ideas - by mlxgarden - 10-12-2026, 06:36 PM
Re: tokens/sec tuning ideas - by rasterhall - 10-12-2026, 07:16 PM
Re: tokens/sec tuning ideas - by quantshed - 10-16-2026, 10:28 PM
Re: tokens/sec tuning ideas - by llm_wren - 10-17-2026, 12:30 PM
Re: tokens/sec tuning ideas - by emberquill - 10-19-2026, 12:48 AM
Re: tokens/sec tuning ideas - by mangotinker73 - 10-12-2026, 09:00 PM
Re: tokens/sec tuning ideas - by fusedhall56 - 10-19-2026, 04:21 AM
Re: tokens/sec tuning ideas - by edgeriver - 10-15-2026, 09:43 PM
Re: tokens/sec tuning ideas - by mintforge - 10-17-2026, 10:46 AM
Re: tokens/sec tuning ideas - by batchfield55 - 10-15-2026, 10:16 PM
Re: tokens/sec tuning ideas - by tensorfield88 - 10-17-2026, 12:04 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)