Model comparison

whisper-large vs nemotron-3.5-asr-streaming-0.6b

At Q4_K_M, nemotron-3.5-asr-streaming-0.6b is the smaller download — 495,831,520 bytes against 996,526,048.

From the file· summed bytes, KV per layer

Side by side

whisper-largenemotron-3.5-asr-streaming-0.6b
Parameters1.5B638M
Architecturewhisperparakeet
Layers32
Native context
Mixture of expertsnono
Quantizations published68
Smallest quantization0.93 GiB0.38 GiB
Q4_K_M0.93 GiB0.46 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
Contextwhisper-largenemotron-3.5-asr-streaming-0.6bRatio
4,096
8,192
16,384
32,768
65,536
131,072