Model comparison
granite-speech-4.1-2b-nar vs cohere-transcribe-03-2026
At Q4_K_M, cohere-transcribe-03-2026 is the smaller download — 1,558,162,944 bytes against 1,560,008,832.
From the file· summed bytes, KV per layer
Side by side
| granite-speech-4.1-2b-nar | cohere-transcribe-03-2026 | |
|---|---|---|
| Parameters | 2.3B | 2.1B |
| Architecture | granite_speech_nar | cohere_asr |
| Layers | 40 | — |
| Native context | 4,096 | — |
| Mixture of experts | no | no |
| Quantizations published | 8 | 11 |
| Smallest quantization | 1.45 GiB | 1.41 GiB |
| Q4_K_M | 1.45 GiB | 1.45 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | granite-speech-4.1-2b-nar | cohere-transcribe-03-2026 | 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 | — | — |