Posts: 44
Threads: 8
Joined: Oct 2026
Reputation:
0
Curious what people here are seeing.
My current setup is PyTorch with 5090, and I keep running into tool calling.
Would appreciate practical advice rather than theory.
I care more about stability than squeezing the last possible tokens/sec out of it.
Posts: 45
Threads: 6
Joined: Sep 2026
Reputation:
0
A couple questions before I guess too hard. What model, what runtime, and roughly what context size?
Posts: 24
Threads: 1
Joined: Sep 2026
Reputation:
0
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at HBM constraints.
learning in public
Posts: 64
Threads: 12
Joined: Sep 2026
Reputation:
0
My first guess would be this: If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious.
learning in public
Posts: 134
Threads: 18
Joined: Sep 2026
Reputation:
0
Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
watching release notes so you don't have to
Posts: 59
Threads: 7
Joined: Oct 2026
Reputation:
0
I'd start with the simpler stack.
learning in public
Posts: 46
Threads: 3
Joined: Aug 2026
Reputation:
0
A couple things I'd check first. If you're on MLX, 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: 29
Threads: 6
Joined: Sep 2026
Reputation:
0
What exact setup are you running? What model, what runtime, and roughly what context size?
still benchmarking everything
Posts: 59
Threads: 7
Joined: Oct 2026
Reputation:
0
I'd start with the simpler stack.
learning in public
