clean API wrappers for local agents for Qwen

[audiorunner74]

Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.

[labnest]

Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up

What exact setup are you running? Are you testing this on M3 Max or something else?

[batchpeak]

What worked for me was pretty simple. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[southpatch]

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.

[edgequill]

I hit almost the same issue last night.

[rocmpath]

Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.