Model comparison
granite-speech-4.1-2b-plus vs parakeet-tdt-0.6b-v3
At Q4_K_M, parakeet-tdt-0.6b-v3 is the smaller download — 485,425,504 bytes against 1,023,646,816.
From the file· summed bytes, KV per layer
Side by side
| granite-speech-4.1-2b-plus | parakeet-tdt-0.6b-v3 | |
|---|---|---|
| Parameters | 2.1B | 627M |
| Architecture | granite_speech | parakeet |
| Layers | 40 | — |
| Native context | 4,096 | — |
| Mixture of experts | no | no |
| Quantizations published | 13 | 10 |
| Smallest quantization | 0.95 GiB | 0.39 GiB |
| Q4_K_M | 0.95 GiB | 0.45 GiB |
| Licence | apache-2.0 | cc-by-4.0 |
KV cache by context
the term that decides long-context viability
| Context | granite-speech-4.1-2b-plus | parakeet-tdt-0.6b-v3 | 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 | — | — |