Quantization publisher

SC117

SC117 publishes 8 quantizations across 6 models in our index, averaging 12.377 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 3 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
6
Quantizations
8
Models covered
6
Avg effective bpw
12.377
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantSC117vsTheirsDifference
Ornith-1.0-35BBF1666.19 GiBbartowski64.61 GiB+2.4%
Qwen-AgentWorld-35B-A3BBF1666.19 GiBunsloth64.61 GiB+2.4%
Ornith-1.0-35BBF1666.19 GiBunsloth64.61 GiB+2.4%

A quantization label describes a target, not a recipe. Publishers make different choices about which tensors to keep at higher precision, and some apply an importance matrix while others don't — so two files both honestly labelled the same thing can differ measurably in size and in quality.

Models they publish