gemma-4
Collection
in mxfp4, mxfp8, and Deckard(qx) • 26 items • Updated • 1
gemma-4-E4B-it-The-DECKARD-V3-Expresso-HERETIC-UNCENSORED-Thinking-mxfp8-mlx
Brainwaves
arc arc/e boolq hswag obkqa piqa wino
mxfp8 0.514,0.706,0.774,0.660,0.436,0.762,0.635
q8 0.514,0.720,0.773,0.660,0.428,0.764,0.646
mxfp4 0.485,0.667,0.809,0.645,0.422,0.758,0.640
Quant Perplexity
mxfp8 8.726 ± 0.087
Baseline model
gemma-4-E4B-it
bf16 0.490,0.674,0.793,0.612,0.416,0.756,0.669
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
- Downloads last month
- 1,579
Model size
3B params
Tensor type
BF16
·
U8 ·
U32 ·
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for nightmedia/gemma-4-E4B-it-The-DECKARD-V3-Expresso-HERETIC-UNCENSORED-Thinking-mxfp8-mlx
Base model
google/gemma-4-E4B-it