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

After a few runs on 5090, I ended up with decent performance, but the setup only really made sense once I adjusted around NVFP4.

Nothing scientific here, just practical notes from a real setup.

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?

I'm especially interested in mistakes worth avoiding.

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 speculative decoding decides everything downstream.

Wondering if this is just where the whole space is heading now.

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.

One thing I keep noticing is that people underestimate KV cache pressure until they actually try to run this stuff for more than one afternoon.

Wondering if this is just where the whole space is heading now.

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

I tried this with DeepSeek using SGLang on Threadripper box. The headline result was better than I expected, but KV cache pressure still ended up being the limiting factor.

Nothing scientific here, just practical notes from a real setup.

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

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

Wanted to compare notes with people doing similar things.

I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling structured output.

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.

Wanted to compare notes with people doing similar things.

I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling embeddings.

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

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: Qwen, LM Studio, 5090, with a lot of attention on router policy.

Maybe useful as a starting point for newer folks.

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

I tried this with Gemma using TensorRT-LLM on 7900 XTX. 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.

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

I'm trying to sanity-check my setup.

I'm mostly working with Mistral in TensorRT-LLM on Threadripper box. The part I'm trying to understand is KV cache pressure.

If you've tested something similar, what did you keep and what did you stop bothering with?