Quantization publisher

GauravGosain

GauravGosain publishes 3 quantizations across 1 models in our index, averaging 9.794 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 4 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
9.794
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantGauravGosainvsTheirsDifference
Qwen3.5-9B-DFlashQ4_K_M0.71 GiBAnbeeld0.71 GiB0.0%
Qwen3.5-9B-DFlashQ8_01.29 GiBAnbeeld1.29 GiB0.0%
Qwen3.5-9B-DFlashBF162.42 GiBAnbeeld2.42 GiB0.0%
Qwen3.5-9B-DFlashQ8_01.29 GiBAtomicChat1.29 GiB0.0%

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
Qwen3.5-9B-DFlash30.71 GiB