Quantization publisher

concedo

concedo publishes 3 quantizations across 1 models in our index, averaging 6.930 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 2 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
1
Quantizations
3
Models covered
1
Avg effective bpw
6.930
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantconcedovsTheirsDifference
GLM-ASR-Nano-2512Q8_01.58 GiBcstr2.27 GiB-30.4%
GLM-ASR-Nano-2512Q4_K0.91 GiBcstr1.23 GiB-26.0%

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

ModelQuantizationsSmallest
GLM-ASR-Nano-251230.91 GiB