Posts: 43
Threads: 3
Joined: Sep 2026
Reputation:
0
Can you fill in a bit more context? Are you testing this on mini PC or something else?
I'm happy to test one more variant if you want a second data point.
mostly local
Posts: 128
Threads: 12
Joined: Sep 2026
Reputation:
0
Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
rack in the garage • local models everywhere
Posts: 50
Threads: 6
Joined: Sep 2026
Reputation:
0
That matches what I was seeing. That matches what I saw on M3 Max. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Posts: 31
Threads: 5
Joined: Sep 2026
Reputation:
0
What exact setup are you running? What model, what runtime, and roughly what context size?
Posts: 37
Threads: 6
Joined: Oct 2026
Reputation:
0
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.