Model comparison

z_image_turbo vs SmolLM2-135M-Instruct

At Q4_K_M, SmolLM2-135M-Instruct is the smaller download — 105,454,144 bytes against 4,511,501,376.

From the file· summed bytes, KV per layer

Side by side

z_image_turboSmolLM2-135M-Instruct
Parameters84M135M
Architecturepigllama
Layers30
Native context8,192
Mixture of expertsnono
Quantizations published1741
Smallest quantization0.16 GiB0.08 GiB
Q4_K_M4.20 GiB0.10 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
Contextz_image_turboSmolLM2-135M-InstructRatio
4,0960.09 GiB
8,1920.18 GiB
16,3840.35 GiB
32,7680.70 GiB
65,5361.41 GiB
131,0722.81 GiB