Gemma 4
on AMD RX 7900 XTX · llama-swap
Summary
User benchmarks Gemma 4 QAT against regular quants on an AMD 7900 XTX. No token/s figures are reported; wall clock times show speedups, including 45% faster and an 83% throughput increase for the 12B QAT.
Models tested are 12B, 26B, 31B and E4B.
The user reports quality as identical.