Inference › Inference Engines › llama.cpp / GGUF v
context size vs speed in GGUF on M3 Max

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
context size vs speed in GGUF on M3 Max
visionyard23 Offline
Member
***
Posts: 55
Threads: 8
Joined: Sep 2026
Reputation: 0
#3
10-19-2026, 12:52 AM
That matches what I was seeing. I ended up in about the same place using llama.cpp. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Apple Silicon • MLX mostly
Find
Reply


Messages In This Thread
Re: context size vs speed in GGUF on M3 Max - by visionyard23 - 10-19-2026, 12:52 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)