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
ModelQuantFreedomAISVRvsTheirsDifference
Qwen3.6-35B-A3B-NVFP4-FastNVFP418.81 GiBcatlilface22.89 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

ModelQuantizationsSmallest
diffusiongemma-26B-A4B-it113.45 GiB
Ministral-3-14B-Instruct-251217.25 GiB
Qwen3.6-35B-A3B-NVFP4-Fast118.81 GiB