Gemma 4 26B (4B active)

User reports Gemma 4 26B-A4B at ~57.6 tok/s at low context on a mixed AMD Vega setup (RX Vega 64 8GB gfx900 + MI50 16GB gfx906). Setup is llama.cpp built for gfx900;gfx906 under ROCm 7.2.1 with Q4_K_M, 8192 context, layer split and tensor-split 1,4; a 1,2 split overloaded the 8GB Vega64 and caused multi-second stalls. Decode falls to ~52.8 tok/s at 8191/8192 tokens. The same model on the single MI50 alone ran roughly 58-59 tok/s at low context and 52-53 tok/s near full 8K context.