Posts: 34
Threads: 6
Joined: Sep 2026
Reputation:
0
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of LM Studio and dual 3090 felt surprisingly usable once I tuned around tool calling.
If someone wants the exact settings I can clean them up and post them.
Posts: 45
Threads: 8
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.
team red, team patient
Posts: 49
Threads: 7
Joined: Oct 2026
Reputation:
0
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at NVFP4.
trying not to rebuild again
Posts: 49
Threads: 9
Joined: Aug 2026
Reputation:
0
Ran a quick check on my box. On M3 Max with llama.cpp, I saw basically the same behavior. The main thing that moved was latency, not quality.
Posts: 39
Threads: 2
Joined: Sep 2026
Reputation:
0
Did a small comparison this afternoon. On 7900 XTX with LM Studio, I saw basically the same behavior.
Posts: 193
Threads: 27
Joined: Aug 2026
Reputation:
0
Quote:Quote:Did a small comparison this afternoon. On 7900 XTX with LM Studio, I saw basically the same behavior.
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at KV cache pressure. Once you know the plain path works, then add the faster path back in piece by piece.
routing beats arguing over one perfect model
Posts: 41
Threads: 6
Joined: Oct 2026
Reputation:
0
Not sure I agree there. I've seen people blame tokens/sec when the real issue was much more mundane.
Posts: 45
Threads: 8
Joined: Sep 2026
Reputation:
0
Can you fill in a bit more context? Are you testing this on 5090 or something else?
team red, team patient
