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

I've gone back and forth between SGLang and MLX for Llama. The interesting difference for me has been embeddings.

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

This is mostly for local work rather than public serving.

Has anyone else run into this?

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

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

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

I've gone back and forth between LM Studio and MLX for DeepSeek. The interesting difference for me has been reranking.

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

This is mostly for local work rather than public serving.

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

One thing I keep noticing is that people underestimate continuous batching 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.

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

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 consumer GPUs.

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

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

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 Ollama and M3 Max.

Simple and boring is a valid answer.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs. The logs were somehow calmer than I was.

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 prefix caching decides everything downstream.

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

I'm trying to sanity-check my setup.

My current setup is TensorRT-LLM with dual 3090, and I keep running into router policy.

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

Wanted to compare notes with people doing similar things.

I'm mostly working with Kimi in Ollama on B200. The part I'm trying to understand is structured output.

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

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 PyTorch and M3 Max.

I'm especially interested in mistakes worth avoiding.

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