Model comparison

JoyAI-Echo vs LTX-2

At Q4_K_M, LTX-2 is the smaller download — 12,840,118,752 bytes against 15,694,613,568.

From the file· summed bytes, KV per layer

Side by side

JoyAI-EchoLTX-2
Parameters12.2B18.9B
Architecturejoyai-gemmaltxv
Layers
Native context
Mixture of expertsnono
Quantizations published528
Smallest quantization8.54 GiB7.48 GiB
Q4_K_M14.62 GiB11.96 GiB
Licence

KV cache by context

the term that decides long-context viability
ContextJoyAI-EchoLTX-2Ratio
4,096
8,192
16,384
32,768
65,536
131,072