Quantization publisher

FabioSantos

FabioSantos publishes 1 quantizations across 1 models in our index, averaging 8.289 effective bits per weight.

From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
8.289
across their files

Models they publish

ModelQuantizationsSmallest
deepseek-r1-distill-llama-8b-unsloth-bnb-4bit17.95 GiB