Model comparison

Wan2.1-T2V-1.3B vs Qwen3-1.7B

At Q4_K_M, Wan2.1-T2V-1.3B is the smaller download — 982,716,640 bytes against 1,107,409,472.

From the file· summed bytes, KV per layer

Side by side

Wan2.1-T2V-1.3BQwen3-1.7B
Parameters1.4B2.0B
Architectureqwen35qwen3
Layers28
Native context40,960
Mixture of expertsnono
Quantizations published3148
Smallest quantization0.61 GiB0.50 GiB
Q4_K_M0.92 GiB1.03 GiB
Licence

KV cache by context

the term that decides long-context viability
ContextWan2.1-T2V-1.3BQwen3-1.7BRatio
4,0960.44 GiB
8,1920.88 GiB
16,3841.75 GiB
32,7683.50 GiB
65,5367.00 GiB
131,07214.00 GiB