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

Two paths both seem viable, but they break down differently once prefill/decode split becomes important.

What would you pick if you had to live with it for a few months?

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

I've gone back and forth between Ollama and LM Studio for Qwen. The interesting difference for me has been token cost.

Interested in tradeoffs more than fan loyalty. Turns out 'just one more test' was a lie.

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

After a few runs on mini PC, I ended up with decent performance, but the setup only really made sense once I adjusted around MoE serving.

Happy to post more details if anyone wants them.

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

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

I tried this with Mistral using TensorRT-LLM on mini PC. The headline result was better than I expected, but speculative decoding still ended up being the limiting factor.

Happy to post more details if anyone wants them.

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 SGLang and Threadripper box.

I'm especially interested in mistakes worth avoiding.

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

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

Just sharing a setup that ended up working reasonably well: Kimi, TensorRT-LLM, M3 Max, with a lot of attention on tail latency.

Feel free to tear it apart if you see something dumb.

This is mostly for local work rather than public serving.

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

Two paths both seem viable, but they break down differently once router policy becomes important.

Interested in tradeoffs more than fan loyalty.

Maybe I'm missing something obvious.

I'm mostly working with Kimi in LM Studio on M3 Max. The part I'm trying to understand is workstation thermals.

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

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 token cost.

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.

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

I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about HBM constraints.

Simple and boring is a valid answer.

If I had to summarize the lesson so far, it would be that clean setup and observability beat clever guesses.