Model comparison
WAN2.2-14B-Rapid-AllInOne vs LTX-2.3
At Q4_K_M, WAN2.2-14B-Rapid-AllInOne is the smaller download — 10,849,052,416 bytes against 14,194,441,248.
From the file· summed bytes, KV per layer
Side by side
| WAN2.2-14B-Rapid-AllInOne | LTX-2.3 | |
|---|---|---|
| Parameters | 17.3B | 9.2B |
| Architecture | wan | qwen35 |
| Layers | — | — |
| Native context | — | — |
| Mixture of experts | no | no |
| Quantizations published | 82 | 92 |
| Smallest quantization | 5.59 GiB | 7.39 GiB |
| Q4_K_M | 10.10 GiB | 13.22 GiB |
| Licence | — | — |
KV cache by context
the term that decides long-context viability
| Context | WAN2.2-14B-Rapid-AllInOne | LTX-2.3 | Ratio |
|---|---|---|---|
| 4,096 | — | — | — |
| 8,192 | — | — | — |
| 16,384 | — | — | — |
| 32,768 | — | — | — |
| 65,536 | — | — | — |
| 131,072 | — | — | — |