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
| Model | Quant | nuofang | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwen3.5-9B-ultra-uncensored-heretic | Q4_K_M | 5.24 GiB | llmfan46 | 5.15 GiB | +1.8% |
| Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED | IQ4_XS | 4.84 GiB | mradermacher | 4.75 GiB | +1.8% |
| Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated | IQ4_XS | 4.84 GiB | mradermacher | 4.87 GiB | -0.6% |
| Qwen3.5-9B-ultra-uncensored-heretic | IQ4_XS | 4.84 GiB | mradermacher | 4.87 GiB | -0.6% |
| Qwen3.5-9B-ultra-uncensored-heretic | Q4_K_S | 4.98 GiB | llmfan46 | 4.98 GiB | +0.2% |
| Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated | Q5_K_M | 6.02 GiB | mradermacher | 6.02 GiB | -0.0% |
| Qwen3.5-9B-ultra-uncensored-heretic | Q4_K_S | 4.98 GiB | mradermacher | 4.98 GiB | -0.0% |
| Qwen3.5-9B-ultra-uncensored-heretic | Q4_K_M | 5.24 GiB | mradermacher | 5.24 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
| Model | Quantizations | Smallest |
|---|---|---|
| Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED | 1 | 4.84 GiB |
| Qwen3.5-9B-ultra-uncensored-heretic | 4 | 4.84 GiB |
| gemma4-e4b-mahou-nsfw | 6 | 4.69 GiB |
| Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated | 2 | 4.84 GiB |