Model comparison
Bernini-R vs LTX-2
At Q4_K_M, Bernini-R is the smaller download — 9,650,100,736 bytes against 12,840,118,752.
From the file· summed bytes, KV per layer
Side by side
KV cache by context
the term that decides long-context viability
| Context | Bernini-R | LTX-2 | Ratio |
|---|---|---|---|
| 4,096 | — | — | — |
| 8,192 | — | — | — |
| 16,384 | — | — | — |
| 32,768 | — | — | — |
| 65,536 | — | — | — |
| 131,072 | — | — | — |