dataset format recommendations

[phaseport36]

My first guess would be this: If you're on LM Studio, 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.

I'm happy to test one more variant if you want a second data point.

[cudapoint]

I tested this tonight. On GB200 with SGLang, I saw basically the same behavior. The main thing that moved was latency, not quality.

[orbitgarden]

A couple things I'd check first. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious.

[forgemixer]

I think the bottleneck is somewhere else. 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.

[routecraft]

Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.

[emberquill]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Qwen and compare from there.