Model comparison
nemotron-3.5-asr-streaming-0.6b vs moonshine-streaming-medium
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| nemotron-3.5-asr-streaming-0.6b | moonshine-streaming-medium | |
|---|---|---|
| Parameters | 638M | 266M |
| Architecture | parakeet | moonshine_streaming |
| Layers | — | 14 |
| Native context | — | 4,096 |
| Mixture of experts | no | no |
| Quantizations published | 8 | 3 |
| Smallest quantization | 0.38 GiB | 0.28 GiB |
| Q4_K_M | 0.46 GiB | — |
| Licence | other | mit |
KV cache by context
the term that decides long-context viability
| Context | nemotron-3.5-asr-streaming-0.6b | moonshine-streaming-medium | Ratio |
|---|---|---|---|
| 4,096 | — | 0.14 GiB | — |
| 8,192 | — | 0.27 GiB | — |
| 16,384 | — | 0.55 GiB | — |
| 32,768 | — | 1.09 GiB | — |
| 65,536 | — | 2.19 GiB | — |
| 131,072 | — | 4.38 GiB | — |