benchmark result I don't trust with LM Studio

[promptspark58]

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.

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

[localtinker]

Did a small comparison this afternoon. On dual 3090 with SGLang, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.