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 router policy decides everything downstream.

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

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

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

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

Maybe useful as a starting point: llama.cpp on dual 3090, keeping embeddings in mind from the start.

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 Phi using LM Studio on M3 Max. 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.

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

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?

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

Maybe I'm missing something obvious.

My current setup is PyTorch with Threadripper box, and I keep running into VRAM headroom.

Would appreciate practical advice rather than theory.

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

This isn't revolutionary, but the combination of SGLang and 7900 XTX felt surprisingly usable once I tuned around continuous batching.

Maybe useful as a starting point for newer folks.

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.

This isn't revolutionary, but the combination of LM Studio and dual 3090 felt surprisingly usable once I tuned around tool calling.

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.

Just sharing a setup that ended up working reasonably well: Phi, MLX, A6000, with a lot of attention on reranking.

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

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 VRAM headroom.

Curious whether that lines up with what other people are seeing. Turns out 'just one more test' was a lie.

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, MLX, 7900 XTX, with a lot of attention on tool calling.

Maybe useful as a starting point for newer folks.