[nnx]

> My M5 Pro can generate 130 tok/s (4 streams) on Gemma 4 26B.

This seems high. At which quantization? Using LM Studio or something else?

Note: Darkbloom seems to run everything on Q8 MLX.

[pants2]

Ah good point, this is using Q4, benchmarked total throughout serving with Llama.cpp.