Model comparison
Wan2.2-Distill-Models vs LTX-2.3
At Q4_K_M, Wan2.2-Distill-Models is the smaller download — 9,661,569,664 bytes against 14,194,441,248.
From the file· summed bytes, KV per layer
Side by side
| Wan2.2-Distill-Models | LTX-2.3 | |
|---|---|---|
| Parameters | 14.3B | 9.2B |
| Architecture | wan | qwen35 |
| Layers | — | — |
| Native context | — | — |
| Mixture of experts | no | no |
| Quantizations published | 67 | 92 |
| Smallest quantization | 4.95 GiB | 7.39 GiB |
| Q4_K_M | 9.00 GiB | 13.22 GiB |
| Licence | — | — |
KV cache by context
the term that decides long-context viability
| Context | Wan2.2-Distill-Models | LTX-2.3 | Ratio |
|---|---|---|---|
| 4,096 | — | — | — |
| 8,192 | — | — | — |
| 16,384 | — | — | — |
| 32,768 | — | — | — |
| 65,536 | — | — | — |
| 131,072 | — | — | — |