Quantization publisher
oncu
oncu publishes 3 quantizations across 1 models in our index, averaging 4.877 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
4.877
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | oncu | vs | Theirs | Difference |
|---|---|---|---|---|---|
| c4ai-command-r7b-12-2024 | Q4_0 | 4.47 GiB | bartowski | 4.48 GiB | -0.3% |
| c4ai-command-r7b-12-2024 | Q4_K_M | 4.71 GiB | saidutta69 | 4.71 GiB | 0.0% |
| c4ai-command-r7b-12-2024 | Q4_K_M | 4.71 GiB | bartowski | 4.71 GiB | -0.0% |
| c4ai-command-r7b-12-2024 | Q4_K_S | 4.50 GiB | bartowski | 4.50 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 |
|---|---|---|
| c4ai-command-r7b-12-2024 | 3 | 4.47 GiB |