Quantization publisher
FreedomAISVR
FreedomAISVR publishes 3 quantizations across 3 models in our index, averaging 5.448 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 1 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
3
Quantizations
3
Models covered
3
Avg effective bpw
5.448
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | FreedomAISVR | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwen3.6-35B-A3B-NVFP4-Fast | NVFP4 | 18.81 GiB | catlilface | 22.89 GiB | -17.9% |
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 |
|---|---|---|
| diffusiongemma-26B-A4B-it | 1 | 13.45 GiB |
| Ministral-3-14B-Instruct-2512 | 1 | 7.25 GiB |
| Qwen3.6-35B-A3B-NVFP4-Fast | 1 | 18.81 GiB |