Model comparison

granite-4.1-8b vs Qwen3-8B

At Q4_K_M, Qwen3-8B is the smaller download — 5,027,783,488 bytes against 5,347,914,400.

From the file· summed bytes, KV per layer

Side by side

granite-4.1-8bQwen3-8B
Parameters8.8B8.2B
Architectureqwen3
Layers4036
Native context131,07240,960
Mixture of expertsnono
Quantizations published3051
Smallest quantization3.05 GiB2.12 GiB
Q4_K_M4.98 GiB4.68 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
Contextgranite-4.1-8bQwen3-8BRatio
4,0960.63 GiB0.56 GiB1.11×
8,1921.25 GiB1.13 GiB1.11×
16,3842.50 GiB2.25 GiB1.11×
32,7685.00 GiB4.50 GiB1.11×
65,53610.00 GiB9.00 GiB1.11×
131,07220.00 GiB18.00 GiB1.11×