Model comparison

nemotron-3.5-asr-streaming-0.6b vs parakeet-unified-en-0.6b

At Q4_K_M, parakeet-unified-en-0.6b is the smaller download — 477,274,496 bytes against 495,831,520.

From the file· summed bytes, KV per layer

Side by side

nemotron-3.5-asr-streaming-0.6bparakeet-unified-en-0.6b
Parameters638M618M
Architectureparakeetparakeet
Layers
Native context
Mixture of expertsnono
Quantizations published86
Smallest quantization0.38 GiB0.44 GiB
Q4_K_M0.46 GiB0.44 GiB
Licenceothercc-by-4.0

KV cache by context

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