Quantization publisher
shb777
shb777 publishes 3 quantizations across 1 models in our index, averaging 6.661 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 3 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
6.661
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | shb777 | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Llama-3.3-8B-Instruct-128K | Q8_0 | 7.95 GiB | TheDrummer | 7.95 GiB | -0.0% |
| Llama-3.3-8B-Instruct-128K | Q6_K | 6.14 GiB | TheDrummer | 6.14 GiB | -0.0% |
| Llama-3.3-8B-Instruct-128K | Q4_K_M | 4.58 GiB | TheDrummer | 4.58 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 |
|---|---|---|
| Llama-3.3-8B-Instruct-128K | 3 | 4.58 GiB |