Posts: 142
Threads: 20
Joined: Sep 2026
Reputation:
0
Spent some time on this today and wanted to compare notes.
Two paths both seem viable, but they break down differently once tool calling becomes important.
Interested in tradeoffs more than fan loyalty.
small models can still be useful
Posts: 58
Threads: 8
Joined: Sep 2026
Reputation:
0
I'd start with the simpler stack.
trying not to rebuild again
Posts: 18
Threads: 3
Joined: Sep 2026
Reputation:
0
I'd approach it in a boring order. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.
trying not to rebuild again
Posts: 82
Threads: 7
Joined: Sep 2026
Reputation:
0
A couple things I'd check first. If you're on LM Studio, 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.
Posts: 199
Threads: 27
Joined: Sep 2026
Reputation:
0
Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
M3 Max • MLX • local-first
Posts: 63
Threads: 4
Joined: Sep 2026
Reputation:
0
following this because I'm in the same boat.
Posts: 76
Threads: 8
Joined: Aug 2026
Reputation:
0
I hit almost the same issue last night.
learning in public
Posts: 211
Threads: 21
Joined: Sep 2026
Reputation:
0
What worked for me was pretty simple. If you're on Ollama, 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.
7900 XTX / ROCm / somehow still optimistic