Quantization publisher
deewu0809
deewu0809 publishes 5 quantizations across 1 models in our index, averaging 16.209 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 6 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
5
Models covered
1
Avg effective bpw
16.209
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | deewu0809 | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwythos-9B-Claude-Mythos-5-1M | Q5_K_M | 12.29 GiB | wepiqx | 12.25 GiB | +0.3% |
| Qwythos-9B-Claude-Mythos-5-1M | Q4_K_M | 10.73 GiB | empero-ai | 10.73 GiB | 0.0% |
| Qwythos-9B-Claude-Mythos-5-1M | Q5_K_M | 12.29 GiB | empero-ai | 12.29 GiB | 0.0% |
| Qwythos-9B-Claude-Mythos-5-1M | Q6_K | 13.95 GiB | empero-ai | 13.95 GiB | 0.0% |
| Qwythos-9B-Claude-Mythos-5-1M | Q8_0 | 17.99 GiB | empero-ai | 17.99 GiB | 0.0% |
| Qwythos-9B-Claude-Mythos-5-1M | BF16 | 33.83 GiB | empero-ai | 33.83 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 |
|---|---|---|
| Qwythos-9B-Claude-Mythos-5-1M | 5 | 10.73 GiB |