do small edge boxes make sense with llama.cpp

[batchfield55]

Did a small comparison this afternoon. On 7900 XTX with TensorRT-LLM, I saw basically the same behavior. I expected the model choice to matter more th

What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.