Model comparison

Bielik-11B-v2.3-Instruct vs gemma-4-E4B-it

At Q4_K_M, gemma-4-E4B-it is the smaller download — 4,977,171,584 bytes against 6,724,050,496. At long context the gap widens: gemma-4-E4B-it's KV cache at 32K is 12.4× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Bielik-11B-v2.3-Instructgemma-4-E4B-it
Parameters11.2B8.0B
Architecturellamagemma4
Layers5042
Native context32,768131,072
Mixture of expertsnono
Quantizations published436
Smallest quantization6.26 GiB3.30 GiB
Q4_K_M6.26 GiB4.64 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextBielik-11B-v2.3-Instructgemma-4-E4B-itRatio
4,0960.78 GiB0.12 GiB6.35×
8,1921.56 GiB0.18 GiB8.79×
16,3843.13 GiB0.29 GiB10.88×
32,7686.25 GiB0.51 GiB12.36×
65,53612.50 GiB0.94 GiB13.25×
131,07225.00 GiB1.82 GiB13.75×