Model comparison

z_image_turbo vs Qwen3-0.6B

At Q4_K_M, Qwen3-0.6B is the smaller download — 396,705,472 bytes against 4,511,501,376.

From the file· summed bytes, KV per layer

Side by side

z_image_turboQwen3-0.6B
Parameters84M752M
Architecturepigqwen3
Layers28
Native context40,960
Mixture of expertsnono
Quantizations published1744
Smallest quantization0.16 GiB0.20 GiB
Q4_K_M4.20 GiB0.37 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
Contextz_image_turboQwen3-0.6BRatio
4,0960.44 GiB
8,1920.88 GiB
16,3841.75 GiB
32,7683.50 GiB
65,5367.00 GiB
131,07214.00 GiB