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

I tried this with Gemma using vLLM on M3 Max. The headline result was better than I expected, but reranking still ended up being the limiting factor.

Curious if anyone else landed in the same place.

I care more about stability than squeezing the last possible tokens/sec out of it.

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.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

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 mini PC felt surprisingly usable once I tuned around consumer GPUs.

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

This is mostly for local work rather than public serving.

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

The more I work with local setups, the more it seems like tail latency decides everything downstream.

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 Kimi using TensorRT-LLM on mini PC. The headline result was better than I expected, but structured output still ended up being the limiting factor.

Happy to post more details if anyone wants them.

Curious what people here are seeing.

My current setup is LM Studio with B200, and I keep running into MoE serving.

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

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

Maybe I'm missing something obvious.

I'm mostly working with FLUX in SGLang on B200. The part I'm trying to understand is tail latency.

Would appreciate practical advice rather than theory.

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

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

I'm comparing two approaches here: keep it simple on B200, or squeeze more out of the stack and deal with the complexity.

Interested in tradeoffs more than fan loyalty.

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

I'm not trying to build a perfect architecture diagram. I just want a sane starting point around MLX and GB200.

Would rather learn from your scars than collect my own all at once.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

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

I've gone back and forth between PyTorch and MLX for Kimi. The interesting difference for me has been HBM constraints.

Trying to avoid rebuilding the whole thing twice.