Quantization publisher
dominguesm
dominguesm publishes 10 quantizations across 1 models in our index, averaging 7.082 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
1
Quantizations
10
Models covered
1
Avg effective bpw
7.082
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | dominguesm | vs | Theirs | Difference |
|---|---|---|---|---|---|
| NVIDIA-Nemotron-Nano-9B-v2 | Q4_0 | 4.94 GiB | bartowski | 4.97 GiB | -0.6% |
| NVIDIA-Nemotron-Nano-9B-v2 | Q4_1 | 5.43 GiB | bartowski | 5.43 GiB | -0.0% |
| NVIDIA-Nemotron-Nano-9B-v2 | Q4_K_M | 6.08 GiB | bartowski | 6.08 GiB | -0.0% |
| NVIDIA-Nemotron-Nano-9B-v2 | Q4_K_S | 5.79 GiB | bartowski | 5.79 GiB | -0.0% |
| NVIDIA-Nemotron-Nano-9B-v2 | Q5_K_M | 6.58 GiB | bartowski | 6.58 GiB | -0.0% |
| NVIDIA-Nemotron-Nano-9B-v2 | Q6_K | 8.51 GiB | bartowski | 8.51 GiB | -0.0% |
| NVIDIA-Nemotron-Nano-9B-v2 | Q2_K | 4.66 GiB | bartowski | 4.66 GiB | -0.0% |
| NVIDIA-Nemotron-Nano-9B-v2 | Q8_0 | 8.81 GiB | bartowski | 8.81 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 |
|---|---|---|
| NVIDIA-Nemotron-Nano-9B-v2 | 10 | 4.66 GiB |