Model comparison

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP vs gemma-3-27b-it-abliterated

At Q4_K_M, gemma-3-27b-it-abliterated is the smaller download — 16,546,689,024 bytes against 36,545,830,912. At long context the gap widens: Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP's KV cache at 32K is 1.6× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTPgemma-3-27b-it-abliterated
Parameters27.8B27.4B
Architectureqwen35gemma3
Layers6462
Native context262,144131,072
Mixture of expertsnono
Quantizations published3436
Smallest quantization10.12 GiB7.86 GiB
Q4_K_M34.04 GiB15.41 GiB
Licenceapache-2.0gemma

KV cache by context

the term that decides long-context viability
ContextQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTPgemma-3-27b-it-abliteratedRatio
4,0960.25 GiB0.92 GiB3.68×
8,1920.50 GiB1.23 GiB2.47×
16,3841.00 GiB1.86 GiB1.86×
32,7682.00 GiB3.11 GiB1.55×
65,5364.00 GiB5.61 GiB1.40×
131,0728.00 GiB10.61 GiB1.33×