Model comparison

whisper-small vs moonshine-streaming-small

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

From the file· summed bytes, KV per layer

Side by side

whisper-smallmoonshine-streaming-small
Parameters242M140M
Architecturewhispermoonshine_streaming
Layers1210
Native context4,096
Mixture of expertsnono
Quantizations published193
Smallest quantization0.08 GiB0.18 GiB
Q4_K_M0.16 GiB
Licenceapache-2.0mit

KV cache by context

the term that decides long-context viability
Contextwhisper-smallmoonshine-streaming-smallRatio
4,0960.08 GiB
8,1920.16 GiB
16,3840.31 GiB
32,7680.63 GiB
65,5361.25 GiB
131,0722.50 GiB