Model comparison

LTX-Video vs Wan2.2-TI2V-5B-Turbo

At Q4_K_M, LTX-Video is the smaller download — 1,416,032,768 bytes against 3,437,927,136.

From the file· summed bytes, KV per layer

Side by side

LTX-VideoWan2.2-TI2V-5B-Turbo
Parameters1.9B5.0B
Architectureltxvwan
Layers
Native context
Mixture of expertsnono
Quantizations published5122
Smallest quantization0.92 GiB1.73 GiB
Q4_K_M1.32 GiB3.20 GiB
Licenceotherapache-2.0

KV cache by context

the term that decides long-context viability
ContextLTX-VideoWan2.2-TI2V-5B-TurboRatio
4,096
8,192
16,384
32,768
65,536
131,072