Model comparison

lingbot-video-moe-30b-a3b vs LTX2.3-10Eros

At Q4_K_M, LTX2.3-10Eros is the smaller download — 14,296,160,672 bytes against 17,026,985,056.

From the file· summed bytes, KV per layer

Side by side

lingbot-video-moe-30b-a3bLTX2.3-10Eros
Parameters30.1B21.0B
Architecturewanltxv
Layers
Native context
Mixture of expertsnono
Quantizations published236
Smallest quantization12.12 GiB9.63 GiB
Q4_K_M15.86 GiB13.31 GiB
Licenceother

KV cache by context

the term that decides long-context viability
Contextlingbot-video-moe-30b-a3bLTX2.3-10ErosRatio
4,096
8,192
16,384
32,768
65,536
131,072