Model comparison
lingbot-video-moe-30b-a3b vs LTX-2
At Q4_K_M, LTX-2 is the smaller download — 12,840,118,752 bytes against 17,026,985,056.
From the file· summed bytes, KV per layer
Side by side
| lingbot-video-moe-30b-a3b | LTX-2 | |
|---|---|---|
| Parameters | 30.1B | 18.9B |
| Architecture | wan | ltxv |
| Layers | — | — |
| Native context | — | — |
| Mixture of experts | no | no |
| Quantizations published | 2 | 28 |
| Smallest quantization | 12.12 GiB | 7.48 GiB |
| Q4_K_M | 15.86 GiB | 11.96 GiB |
| Licence | other | — |
KV cache by context
the term that decides long-context viability
| Context | lingbot-video-moe-30b-a3b | LTX-2 | Ratio |
|---|---|---|---|
| 4,096 | — | — | — |
| 8,192 | — | — | — |
| 16,384 | — | — | — |
| 32,768 | — | — | — |
| 65,536 | — | — | — |
| 131,072 | — | — | — |