Quantization publisher

nuofang

nuofang publishes 13 quantizations across 4 models in our index, averaging 4.979 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 8 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
4
Quantizations
13
Models covered
4
Avg effective bpw
4.979
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantnuofangvsTheirsDifference
Qwen3.5-9B-ultra-uncensored-hereticQ4_K_M5.24 GiBllmfan465.15 GiB+1.8%
Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSOREDIQ4_XS4.84 GiBmradermacher4.75 GiB+1.8%
Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliteratedIQ4_XS4.84 GiBmradermacher4.87 GiB-0.6%
Qwen3.5-9B-ultra-uncensored-hereticIQ4_XS4.84 GiBmradermacher4.87 GiB-0.6%
Qwen3.5-9B-ultra-uncensored-hereticQ4_K_S4.98 GiBllmfan464.98 GiB+0.2%
Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliteratedQ5_K_M6.02 GiBmradermacher6.02 GiB-0.0%
Qwen3.5-9B-ultra-uncensored-hereticQ4_K_S4.98 GiBmradermacher4.98 GiB-0.0%
Qwen3.5-9B-ultra-uncensored-hereticQ4_K_M5.24 GiBmradermacher5.24 GiB-0.0%

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