Quantization publisher
ggfox00000
ggfox00000 publishes 3 quantizations across 1 models in our index, averaging 6.609 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 4 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
6.609
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | ggfox00000 | vs | Theirs | Difference |
|---|---|---|---|---|---|
| DeepSeek-V2-Lite-Chat | Q4_K_M | 9.66 GiB | second-state | 9.65 GiB | 0.0% |
| DeepSeek-V2-Lite-Chat | Q5_K_M | 11.04 GiB | second-state | 11.04 GiB | 0.0% |
| DeepSeek-V2-Lite-Chat | Q8_0 | 15.56 GiB | legraphista | 15.56 GiB | 0.0% |
| DeepSeek-V2-Lite-Chat | Q8_0 | 15.56 GiB | second-state | 15.56 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 |
|---|---|---|
| DeepSeek-V2-Lite-Chat | 3 | 9.66 GiB |