Model comparison

whisper-small vs GigaAM-v3

At Q4_K_M, whisper-small is the smaller download — 171,630,656 bytes against 182,497,888.

From the file· summed bytes, KV per layer

Side by side

whisper-smallGigaAM-v3
Parameters242M223M
Architecturewhispergigaam
Layers12
Native context
Mixture of expertsnono
Quantizations published1918
Smallest quantization0.08 GiB0.17 GiB
Q4_K_M0.16 GiB0.17 GiB
Licenceapache-2.0mit

KV cache by context

the term that decides long-context viability
Contextwhisper-smallGigaAM-v3Ratio
4,096
8,192
16,384
32,768
65,536
131,072