         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.516,0.709,0.794,0.649,0.416,0.760,0.639

Perplexity
mxfp8    8.836 ± 0.091
mxfp4    9.980 ± 0.108

Baseline model

brainwaves

gemma-4-E4B-it
         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.480,0.656,0.797,0.608,0.400,0.755,0.665
mxfp4    0.455,0.607,0.851,0.585,0.402,0.744,0.651

Quant    Perplexity      Peak Memory   Tokens/sec
mxfp8    35.937 ± 0.525  14.80 GB      1153
mxfp4    36.746 ± 0.534  11.06 GB      1030

See parent model for instructions on install and use with Transformers.

-G

nightmedia/gemma-4-E4B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-mxfp8-mlx

gemma-4-E4B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-mxfp8-mlx

nightmedia/
gemma-4-E4B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-mxfp8-mlx