Model comparison

EXAONE-3.5-7.8B-Instruct vs Qwen3-8B

At Q4_K_M, EXAONE-3.5-7.8B-Instruct is the smaller download — 4,770,650,016 bytes against 5,027,783,488.

From the file· summed bytes, KV per layer

Side by side

EXAONE-3.5-7.8B-InstructQwen3-8B
Parameters7.8B8.2B
Architectureexaoneqwen3
Layers36
Native context32,76840,960
Mixture of expertsnono
Quantizations published2751
Smallest quantization2.46 GiB2.12 GiB
Q4_K_M4.44 GiB4.68 GiB
Licenceotherapache-2.0

KV cache by context

the term that decides long-context viability
ContextEXAONE-3.5-7.8B-InstructQwen3-8BRatio
4,0960.56 GiB
8,1921.13 GiB
16,3842.25 GiB
32,7684.50 GiB
65,5369.00 GiB
131,07218.00 GiB