MOSS on a 3090: Q2 failed, AWQ4 stayed closer

Every profile began with the pinned BF16 generator. The comparison reused fixed reference codes and an FP32 decoder for the main quality measurements, keeping codec changes separate from generator quantization.

Quantize from the original

The useful and rejected candidates

Original BF16 had mean WavLM cosine 0.9837, UTMOSv2 3.192 and normalized pooled character error 1.53%. AWQ4 measured 0.9828, 3.166 and 1.70%. AutoRoundQ3 measured 0.9818, 3.241 and 2.04%.

Sensitivity Q2 fell to cosine 0.6845 and character error 121.85%; insertions can make character error exceed 100%. It was rejected. Nominal Q2/Q3 labels did not describe uniform effective storage: protected tensors and metadata raised effective bits per weight.

Memory and speed are separate

Recorded generator peaks ranged from 7.22 GiB for Q2 to 17.78 GiB for BF16. Those peaks included the resident reference decoder and exclude the separately measured extra allocation of FP32 decoding. The combined decoder RTF is a pooled timing estimate, not a single-process serving benchmark.

AWQ4 was a fidelity candidate and AutoRoundQ3 promising on automatic proxies. Neither substitutes for blinded human listening, and this CUDA prototype does not demonstrate Apple Silicon performance.

Evidence and publication boundary

This is an edited account of the recorded experiment. The linked archive is private; the methods, aggregate findings and limits are included above. Reference recordings, raw conversations, authentication material and workstation configuration are excluded.