Quantization publisher
zetasepic
zetasepic publishes 7 quantizations across 1 models in our index, averaging 5.222 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 7 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
7
Models covered
1
Avg effective bpw
5.222
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | zetasepic | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwen2.5-72B | IQ4_XS | 37.40 GiB | ThomasBaruzier | 36.98 GiB | +1.1% |
| Qwen2.5-72B | Q2_K | 27.76 GiB | ThomasBaruzier | 27.76 GiB | -0.0% |
| Qwen2.5-72B | IQ3_M | 33.07 GiB | ThomasBaruzier | 33.07 GiB | -0.0% |
| Qwen2.5-72B | Q4_K_M | 44.16 GiB | ThomasBaruzier | 44.16 GiB | -0.0% |
| Qwen2.5-72B | Q6_K | 59.93 GiB | ThomasBaruzier | 59.93 GiB | -0.0% |
| Qwen2.5-72B | Q8_0 | 71.96 GiB | ThomasBaruzier | 71.96 GiB | -0.0% |
| Qwen2.5-72B | Q3_K_M | 35.11 GiB | ThomasBaruzier | 35.11 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 |
|---|---|---|
| Qwen2.5-72B | 7 | 27.76 GiB |