Model comparison

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP vs InternVL3_5-30B-A3B

At Q4_K_M, InternVL3_5-30B-A3B is the smaller download — 18,632,180,352 bytes against 36,545,830,912.

From the file· summed bytes, KV per layer

Side by side

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTPInternVL3_5-30B-A3B
Parameters27.8B30.8B
Architectureqwen35qwen3moe
Layers64
Native context262,144
Mixture of expertsnono
Quantizations published3430
Smallest quantization10.12 GiB7.05 GiB
Q4_K_M34.04 GiB17.35 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTPInternVL3_5-30B-A3BRatio
4,0960.25 GiB
8,1920.50 GiB
16,3841.00 GiB
32,7682.00 GiB
65,5364.00 GiB
131,0728.00 GiB