Quantization publisher
Radamanthys11
Radamanthys11 publishes 4 quantizations across 2 models in our index, averaging 12.536 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
2
Quantizations
4
Models covered
2
Avg effective bpw
12.536
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | Radamanthys11 | vs | Theirs | Difference |
|---|---|---|---|---|---|
| gemma-4-31B-it-assistant | F16 | 0.89 GiB | NotMe404 | 0.89 GiB | 0.0% |
| gemma-4-31B-it-assistant | F16 | 0.89 GiB | AtomicChat | 0.89 GiB | 0.0% |
| gemma-4-31B-it-assistant | Q8_0 | 0.48 GiB | NotMe404 | 0.48 GiB | 0.0% |
| gemma-4-31B-it-assistant | Q8_0 | 0.48 GiB | AtomicChat | 0.48 GiB | 0.0% |
| gemma-4-26B-A4B-it-assistant | F16 | 0.80 GiB | AtomicChat | 0.80 GiB | -0.0% |
| gemma-4-26B-A4B-it-assistant | Q8_0 | 0.43 GiB | AtomicChat | 0.43 GiB | -0.0% |
| gemma-4-26B-A4B-it-assistant | Q8_0 | 0.43 GiB | RachidAR | 0.43 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 |
|---|---|---|
| gemma-4-26B-A4B-it-assistant | 2 | 0.43 GiB |
| gemma-4-31B-it-assistant | 2 | 0.48 GiB |