This is currently a STATIC quant, because the imatrix tool seems to be broken with Gemma 4 (>100 ppl). I will update with an imatrix once I can verify correctness.
6.52 bpw, a mixture of Q6_K, Q5_K, and Q8_0
Fits ~75k F16 CTX + MMPROJ on a 24GiB GPU, or ~150k CTX without vision. Measured on a DE, not headless.