Quantization publisher

MaralGPT

MaralGPT publishes 4 quantizations across 1 models in our index, averaging 7.844 effective bits per weight.

From the file· summed file bytes
Repositories
1
Quantizations
4
Models covered
1
Avg effective bpw
7.844
across their files

Models they publish

ModelQuantizationsSmallest
MaralGPT-Mythos-9B-260643.56 GiB