+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Model Comparisons (https://www.datasculpting.ai/inference/forumdisplay.php?fid=67)
+--- Thread: flux pipeline local tips on Threadripper box (/showthread.php?tid=1313)
Pages:
1
2
Re: flux pipeline local tips on Threadripper box - cobaltworks25 - 10-18-2026
That matches what I was seeing. The pattern around tokens/sec has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: flux pipeline local tips on Threadripper box - homelabhenry - 10-19-2026
Can you fill in a bit more context? Is this local-only or are you routing anything externally?
Re: flux pipeline local tips on Threadripper box - mlxgarden - 10-19-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at small local stacks.
Re: flux pipeline local tips on Threadripper box - embershed99 - 10-19-2026
Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: flux pipeline local tips on Threadripper box - circuitwire58 - 10-19-2026
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.
Re: flux pipeline local tips on Threadripper box - thetagrid15 - 10-19-2026
Appreciate the detail. I ended up in about the same place using MLX. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.