Model comparison
parakeet-unified-en-0.6b vs granite-speech-4.1-2b-plus
At Q4_K_M, parakeet-unified-en-0.6b is the smaller download — 477,274,496 bytes against 1,023,646,816.
From the file· summed bytes, KV per layer
Side by side
| parakeet-unified-en-0.6b | granite-speech-4.1-2b-plus | |
|---|---|---|
| Parameters | 618M | 2.1B |
| Architecture | parakeet | granite_speech |
| Layers | — | 40 |
| Native context | — | 4,096 |
| Mixture of experts | no | no |
| Quantizations published | 6 | 13 |
| Smallest quantization | 0.44 GiB | 0.95 GiB |
| Q4_K_M | 0.44 GiB | 0.95 GiB |
| Licence | cc-by-4.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | parakeet-unified-en-0.6b | granite-speech-4.1-2b-plus | Ratio |
|---|---|---|---|
| 4,096 | — | 0.31 GiB | — |
| 8,192 | — | 0.63 GiB | — |
| 16,384 | — | 1.25 GiB | — |
| 32,768 | — | 2.50 GiB | — |
| 65,536 | — | 5.00 GiB | — |
| 131,072 | — | 10.00 GiB | — |