Model comparison

whisper-base.en vs SenseVoiceSmall

At Q4_K_M, whisper-base.en is the smaller download — 58,794,272 bytes against 145,738,304.

From the file· summed bytes, KV per layer

Side by side

whisper-base.enSenseVoiceSmall
Parameters73M234M
Architecturewhispersensevoice
Layers6
Native context
Mixture of expertsnono
Quantizations published69
Smallest quantization0.05 GiB0.13 GiB
Q4_K_M0.05 GiB0.14 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
Contextwhisper-base.enSenseVoiceSmallRatio
4,096
8,192
16,384
32,768
65,536
131,072