Model comparison
VibeVoice-Large vs Voxtral-Mini-4B-Realtime-2602
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| VibeVoice-Large | Voxtral-Mini-4B-Realtime-2602 | |
|---|---|---|
| Parameters | 9.3B | 4.4B |
| Architecture | vibevoice-asr | voxtral_realtime |
| Layers | — | 26 |
| Native context | — | 131,072 |
| Mixture of experts | no | no |
| Quantizations published | 7 | 8 |
| Smallest quantization | 5.74 GiB | 2.35 GiB |
| Q4_K_M | — | 2.64 GiB |
| Licence | mit | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | VibeVoice-Large | Voxtral-Mini-4B-Realtime-2602 | Ratio |
|---|---|---|---|
| 4,096 | — | — | — |
| 8,192 | — | — | — |
| 16,384 | — | — | — |
| 32,768 | — | — | — |
| 65,536 | — | — | — |
| 131,072 | — | — | — |