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
| Model | Quant | GauravGosain | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwen3.5-9B-DFlash | Q4_K_M | 0.71 GiB | Anbeeld | 0.71 GiB | 0.0% |
| Qwen3.5-9B-DFlash | Q8_0 | 1.29 GiB | Anbeeld | 1.29 GiB | 0.0% |
| Qwen3.5-9B-DFlash | BF16 | 2.42 GiB | Anbeeld | 2.42 GiB | 0.0% |
| Qwen3.5-9B-DFlash | Q8_0 | 1.29 GiB | AtomicChat | 1.29 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-DFlash | 3 | 0.71 GiB |