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

This isn't revolutionary, but the combination of Ollama and 4090 felt surprisingly usable once I tuned around long context.

Maybe useful as a starting point for newer folks.

Curious what people here are seeing.

I'm mostly working with Gemma in PyTorch on 7900 XTX. The part I'm trying to understand is quant drift.

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

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

Short version: MLX behaved well for me, but only after I stopped ignoring small local stacks.

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

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

I've gone back and forth between Ollama and vLLM for FLUX. The interesting difference for me has been INT4.

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

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 KV cache pressure decides everything downstream.

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

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

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

Maybe useful as a starting point: LM Studio on M3 Max, keeping structured output in mind from the start.

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

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.

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

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

I've gone back and forth between vLLM and vLLM for Kimi. The interesting difference for me has been reranking.

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

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

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

Maybe useful as a starting point: MLX on dual 3090, keeping continuous batching in mind from the start.

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

The part that surprised me was how much the boring details mattered more than the model choice.

I figured I'd ask here before changing everything.

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

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