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 KV cache pressure.

Curious whether that lines up with what other people are seeing.

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 LM Studio and 4090.

I'm especially interested in mistakes worth avoiding.

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.

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 B200.

I'm especially interested in mistakes worth avoiding.

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

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 long context decides everything downstream.

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.

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

I tried this with Mistral using LM Studio on 7900 XTX. The headline result was better than I expected, but tokens/sec still ended up being the limiting factor.

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

I expected the biggest difference to come from the model, but the stack around it mattered at least as much.

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

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

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

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 HBM constraints decides everything downstream.

Curious whether that lines up with what other people are seeing.

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

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

I tried this with Gemma using PyTorch on Threadripper box. The headline result was better than I expected, but router policy still ended up being the limiting factor.

Happy to post more details if anyone wants them.

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 INT4.

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