Model comparison
nemotron-3.5-asr-streaming-0.6b vs whisper-large-v3-turbo
At Q4_K_M, nemotron-3.5-asr-streaming-0.6b is the smaller download — 495,831,520 bytes against 536,069,728.
From the file· summed bytes, KV per layer
Side by side
| nemotron-3.5-asr-streaming-0.6b | whisper-large-v3-turbo | |
|---|---|---|
| Parameters | 638M | 809M |
| Architecture | parakeet | whisper |
| Layers | — | 32 |
| Native context | — | — |
| Mixture of experts | no | no |
| Quantizations published | 8 | 31 |
| Smallest quantization | 0.38 GiB | 0.27 GiB |
| Q4_K_M | 0.46 GiB | 0.50 GiB |
| Licence | other | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | nemotron-3.5-asr-streaming-0.6b | whisper-large-v3-turbo | Ratio |
|---|---|---|---|
| 4,096 | — | — | — |
| 8,192 | — | — | — |
| 16,384 | — | — | — |
| 32,768 | — | — | — |
| 65,536 | — | — | — |
| 131,072 | — | — | — |