best GGUF for 24GB VRAM: early impressions

[northcraft90]

Appreciate the detail. The pattern around router policy has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[vrambandit]

Thanks, that helps. The pattern around quant drift has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[southden]

Tried to reproduce it just now. On M3 Max with llama.cpp, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.

[dockridge]

What exact setup are you running? Is this local-only or are you routing anything externally?

[vrambandit]

I hit almost the same issue last night.