Posts: 40
Threads: 4
Joined: Sep 2026
Reputation:
0
I figured I'd ask here before changing everything.
I'm mostly working with Kimi in Ollama on GB200. The part I'm trying to understand is consumer GPUs.
If you've tested something similar, what did you keep and what did you stop bothering with?
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
small models can still be good
Posts: 38
Threads: 7
Joined: Oct 2026
Reputation:
0
Tried to reproduce it just now. On GB200 with PyTorch, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.
Posts: 18
Threads: 3
Joined: Sep 2026
Reputation:
0
following this because I'm in the same boat.
trying not to rebuild again
Posts: 26
Threads: 3
Joined: Sep 2026
Reputation:
0
following this because I'm in the same boat.
Posts: 36
Threads: 8
Joined: Aug 2026
Reputation:
0
That matches what I was seeing. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Posts: 76
Threads: 12
Joined: Aug 2026
Reputation:
0
What exact setup are you running? Are you testing this on mini PC or something else?
Posts: 128
Threads: 12
Joined: Sep 2026
Reputation:
0
Quote:What exact setup are you running? Are you testing this on mini PC or something else?
worth checking the driver first.
rack in the garage • local models everywhere
Posts: 42
Threads: 4
Joined: Oct 2026
Reputation:
0
A couple things I'd check first. If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.
curious and caffeinated
Posts: 123
Threads: 18
Joined: Sep 2026
Reputation:
0
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly.
post logs or it didn't happen
