which hosted model is actually worth paying for

[circuitkite]

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

Short version: PyTorch behaved well for me, but only after I stopped ignoring NVFP4.

Happy to post more details if anyone wants them.

[routecraft]

I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[cobaltlab]

My first guess would be this: If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious.

[routecraft]

subscribed, curious where this lands.

[localtinker]

I'd approach it in a boring order. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.

[oxideworks59]

Need a little more detail here. What model, what runtime, and roughly what context size?

[routecraft]

following this because I'm in the same boat.

[bytepilot]

Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.