Model comparison

elios_offline vs Qwen3.6-27B

At Q4_K_M, Qwen3.6-27B is the smaller download — 16,547,397,888 bytes against 18,687,058,176.

From the file· summed bytes, KV per layer

Side by side

elios_offlineQwen3.6-27B
Parameters30.7B27.8B
Architecturegemma4qwen35
Layers64
Native context262,144
Mixture of expertsnono
Quantizations published3440
Smallest quantization6.66 GiB8.74 GiB
Q4_K_M17.40 GiB15.41 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
Contextelios_offlineQwen3.6-27BRatio
4,0960.25 GiB
8,1920.50 GiB
16,3841.00 GiB
32,7682.00 GiB
65,5364.00 GiB
131,0728.00 GiB
elios_offline vs Qwen3.6-27B — size, memory and hardware fit — ossmodeldb