Quantization publisher
theprint
theprint publishes 56 quantizations across 3 models in our index, averaging 6.063 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 2 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
5
Quantizations
56
Models covered
3
Avg effective bpw
6.063
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | theprint | vs | Theirs | Difference |
|---|---|---|---|---|---|
| mistral-7b-v0.3-bnb-4bit | Q4_K_M | 4.07 GiB | ebowwa | 4.07 GiB | 0.0% |
| mistral-7b-v0.3-bnb-4bit | Q4_K_M | 4.07 GiB | ebowwa | 4.07 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 |
|---|---|---|
| Qwen3.5-2B | 38 | 0.75 GiB |
| meta-llama-3.1-8b-bnb-4bit | 9 | 3.41 GiB |
| mistral-7b-v0.3-bnb-4bit | 9 | 2.95 GiB |