Model comparison

Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved vs Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP

At Q4_K_M, Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved is the smaller download — 17,211,797,600 bytes against 36,545,830,912.

From the file· summed bytes, KV per layer

Side by side

Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-PreservedQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP
Parameters27.4B27.8B
Architectureqwen35qwen35
Layers6464
Native context262,144262,144
Mixture of expertsnono
Quantizations published2534
Smallest quantization10.12 GiB10.12 GiB
Q4_K_M16.03 GiB34.04 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.6-27B-uncensored-heretic-v2-Native-MTP-PreservedQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTPRatio
4,0960.25 GiB0.25 GiB1.00×
8,1920.50 GiB0.50 GiB1.00×
16,3841.00 GiB1.00 GiB1.00×
32,7682.00 GiB2.00 GiB1.00×
65,5364.00 GiB4.00 GiB1.00×
131,0728.00 GiB8.00 GiB1.00×