gemma-4-31B-it-Claude-Opus-Distill-v2-mxfp8-mlx

Brainwaves

         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.532,0.667,0.900,0.694,0.384,0.765,0.676

         Perplexity      Peak memory  Tokens/sec
mxfp8    11.160 ± 0.124  39.69 GB     170

Previous version
mxfp8    0.540,0.708,0.891,0.733,0.434,0.788,0.686

         Perplexity      Peak memory  Tokens/sec
mxfp8    32.665 ± 0.472  39.54 GB     146

Base model
gemma-4-31B-it
qx86-hi  0.496,0.653,0.901,0.624,0.380,0.732,0.653

Previous model
gemma-3-27b-it-heretic
q8       0.557,0.711,0.868,0.533,0.452,0.706,0.695

Similar models

         arc   arc/e boolq hswag obkqa piqa  wino
DavidAU/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking
Instruct
mxfp8    0.583,0.747,0.894,0.734,0.430,0.787,0.719

DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking
qx86-hi  0.431,0.505,0.426,0.670,0.376,0.766,0.710
Downloads last month
994
Safetensors
Model size
9B params
Tensor type
U8
·
U32
·
BF16
·
MLX
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-4-31B-it-Claude-Opus-Distill-v2-mxfp8-mlx

Collection including nightmedia/gemma-4-31B-it-Claude-Opus-Distill-v2-mxfp8-mlx