Spent some time on this today and wanted to compare notes.

I'm comparing two approaches here: keep it simple on dual 3090, or squeeze more out of the stack and deal with the complexity.

Trying to avoid rebuilding the whole thing twice.

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.

This keeps coming up in conversation so I figured I'd start a thread.

It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with structured output.

Maybe obvious to some of you, but it clicked for me this week.

Did a bit of testing and thought I'd post the result here.

I tried this with Phi using llama.cpp on A6000. The headline result was better than I expected, but VRAM headroom still ended up being the limiting factor.

Happy to post more details if anyone wants them.

Maybe I'm missing something obvious.

My current setup is PyTorch with A6000, and I keep running into prefill/decode split.

Would appreciate practical advice rather than theory.

Did a bit of testing and thought I'd post the result here.

I tried this with FLUX using vLLM on 5090. The headline result was better than I expected, but small local stacks still ended up being the limiting factor.

Curious if anyone else landed in the same place.

This keeps coming up in conversation so I figured I'd start a thread.

It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with tail latency.

Maybe obvious to some of you, but it clicked for me this week.

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.

Thought I'd post a small recipe because a lot of threads ask similar things.

This isn't revolutionary, but the combination of Ollama and 7900 XTX felt surprisingly usable once I tuned around structured output.

If someone wants the exact settings I can clean them up and post them.

Thought I'd post a small recipe because a lot of threads ask similar things.

This isn't revolutionary, but the combination of llama.cpp and 7900 XTX felt surprisingly usable once I tuned around prefill/decode split.

Maybe useful as a starting point for newer folks.

I'm trying to sanity-check my setup.

My current setup is LM Studio with A6000, and I keep running into VRAM headroom.

Not looking for the perfect answer, mostly what worked in real use.

This is mostly for local work rather than public serving.

Posting this in case it saves someone else a little time.

If you were starting from scratch today for this use case, what would you choose first and what would you ignore?

Simple and boring is a valid answer.