Model comparison

MOSS-Transcribe-Diarize vs whisper-large-v3

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

MOSS-Transcribe-Diarizewhisper-large-v3
Parameters909M1.5B
Architecturecamppluswhisper
Layers2832
Native context131,072
Mixture of expertsnono
Quantizations published1118
Smallest quantization0.50 GiB0.49 GiB
Q4_K_M0.93 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextMOSS-Transcribe-Diarizewhisper-large-v3Ratio
4,0960.44 GiB
8,1920.88 GiB
16,3841.75 GiB
32,7683.50 GiB
65,5367.00 GiB
131,07214.00 GiB