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 Threadripper box felt surprisingly usable once I tuned around token cost.

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

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.

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

Wondering if this is just where the whole space is heading now. I keep promising myself this is the last rebuild.

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

One thing I keep noticing is that people underestimate prefix caching 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.

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: Mistral, llama.cpp, 4090, with a lot of attention on reranking.

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

This is mostly for local work rather than public serving.

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 structured output.

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 Gemma using MLX on 4090. The headline result was better than I expected, but continuous batching 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.

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

I tried this with Mistral using LM Studio on GB200. The headline result was better than I expected, but VRAM headroom still ended up being the limiting factor.

Happy to post more details if anyone wants them.

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

I've gone back and forth between PyTorch and Ollama for Kimi. The interesting difference for me has been router policy.

Interested in tradeoffs more than fan loyalty.

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

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, vLLM, dual 3090, with a lot of attention on tail latency.

Maybe useful as a starting point for newer folks.

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.

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

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

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