Quantization publisher
dranger003
dranger003 publishes 47 quantizations across 2 models in our index, averaging 4.463 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
2
Quantizations
47
Models covered
2
Avg effective bpw
4.463
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | dranger003 | vs | Theirs | Difference |
|---|---|---|---|---|---|
| c4ai-command-r-v01 | Q2_K | 12.87 GiB | DavidAU | 12.87 GiB | 0.0% |
| c4ai-command-r-plus | Q3_K_M | 47.48 GiB | pmysl | 47.48 GiB | 0.0% |
| c4ai-command-r-plus | Q5_K_M | 68.57 GiB | pmysl | 68.57 GiB | 0.0% |
| c4ai-command-r-plus | Q5_K_S | 66.87 GiB | pmysl | 66.87 GiB | 0.0% |
| c4ai-command-r-plus | Q3_K_L | 51.60 GiB | pmysl | 51.60 GiB | 0.0% |
| c4ai-command-r-plus | Q2_K | 36.78 GiB | pmysl | 36.78 GiB | 0.0% |
| c4ai-command-r-plus | Q4_K_M | 58.44 GiB | pmysl | 58.44 GiB | 0.0% |
| c4ai-command-r-plus | Q4_K_S | 55.55 GiB | pmysl | 55.55 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-r-v01 | 24 | 7.94 GiB |
| c4ai-command-r-plus | 23 | 21.59 GiB |