Quantization publisher
ChrisColeTech
ChrisColeTech publishes 4 quantizations across 1 models in our index, averaging 5.344 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
4
Models covered
1
Avg effective bpw
5.344
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | ChrisColeTech | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwen-Image-Edit-2511 | Q4_K_M | 10.86 GiB | unsloth | 12.34 GiB | -12.0% |
| Qwen-Image-Edit-2511 | Q4_K_M | 10.86 GiB | Daex032 | 12.34 GiB | -12.0% |
| Qwen-Image-Edit-2511 | Q6_K | 15.63 GiB | unsloth | 15.70 GiB | -0.4% |
| Qwen-Image-Edit-2511 | Q6_K | 15.63 GiB | Daex032 | 15.70 GiB | -0.4% |
| Qwen-Image-Edit-2511 | Q8_0 | 20.23 GiB | unsloth | 20.27 GiB | -0.2% |
| Qwen-Image-Edit-2511 | Q8_0 | 20.23 GiB | Daex032 | 20.27 GiB | -0.2% |
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 |
|---|---|---|
| Qwen-Image-Edit-2511 | 4 | 4.13 GiB |