Quantization publisher

spiritfather

spiritfather publishes 34 quantizations across 1 models in our index, averaging 4.510 effective bits per weight.

From the file· summed file bytes
Repositories
2
Quantizations
34
Models covered
1
Avg effective bpw
4.510
across their files

Models they publish

ModelQuantizationsSmallest
Gemma4-Gutenberg-26B-A4B-lora347.72 GiB