Quantization publisher

bottlecapai

bottlecapai publishes 4 quantizations across 1 models in our index, averaging 8.988 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
1
Quantizations
4
Models covered
1
Avg effective bpw
8.988
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantbottlecapaivsTheirsDifference
ThinkingCap-Qwen3.6-27BQ6_K20.89 GiBbartowski21.85 GiB-4.4%
ThinkingCap-Qwen3.6-27BQ4_K_M15.66 GiBbartowski16.55 GiB-5.4%
ThinkingCap-Qwen3.6-27BQ8_027.05 GiBbartowski27.12 GiB-0.2%

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
ThinkingCap-Qwen3.6-27B415.66 GiB