Quantization publisher
juiceb0xc0de
juiceb0xc0de publishes 18 quantizations across 2 models in our index, averaging 6.329 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
18
Models covered
2
Avg effective bpw
6.329
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | juiceb0xc0de | vs | Theirs | Difference |
|---|---|---|---|---|---|
| llama-3.2-3b-instruct | Q8_0 | 3.19 GiB | mfielding92 | 3.19 GiB | -0.0% |
| llama-3.2-3b-instruct | Q4_K_M | 1.88 GiB | Zynerji | 1.88 GiB | -0.0% |
| llama-3.2-3b-instruct | Q5_K_M | 2.16 GiB | Zynerji | 2.16 GiB | -0.0% |
| llama-3.2-3b-instruct | Q6_K | 2.46 GiB | Zynerji | 2.46 GiB | -0.0% |
| llama-3.2-3b-instruct | Q8_0 | 3.19 GiB | Zynerji | 3.19 GiB | -0.0% |
| llama-3.2-3b-instruct | IQ3_M | 1.49 GiB | Zynerji | 1.49 GiB | -0.0% |
| llama-3.2-3b-instruct | IQ4_XS | 1.70 GiB | Zynerji | 1.70 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 |
|---|---|---|
| Meta-Llama-3.1-8B-Instruct | 9 | 2.43 GiB |
| llama-3.2-3b-instruct | 9 | 1.02 GiB |