Posts: 25
Threads: 4
Joined: Sep 2026
Reputation:
0
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at long context. Not glamorous advice, but repeatable baselines save a lot of time.
curious and caffeinated
Posts: 22
Threads: 1
Joined: Sep 2026
Reputation:
0
My first guess would be this: On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Posts: 39
Threads: 2
Joined: Sep 2026
Reputation:
0
A couple questions before I guess too hard. Is this local-only or are you routing anything externally?
Posts: 40
Threads: 3
Joined: Sep 2026
Reputation:
0
Ran a quick check on my box. On Threadripper box with MLX, I saw basically the same behavior. I expected the model choice to matter more than it did.
Apple Silicon • MLX mostly
Posts: 44
Threads: 3
Joined: Oct 2026
Reputation:
0
Interesting, I hadn't tried that. I ended up in about the same place using PyTorch. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.