Model comparison

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP vs Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated

At Q4_K_M, Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated is the smaller download — 18,556,687,872 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 1.5× 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-MTPHuihui-Qwen3-VL-30B-A3B-Instruct-abliterated
Parameters27.8B31.1B
Architectureqwen35qwen3vlmoe
Layers6448
Native context262,144262,144
Mixture of expertsnoyes, 128 experts
Quantizations published3454
Smallest quantization10.12 GiB5.98 GiB
Q4_K_M34.04 GiB17.28 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-MTPHuihui-Qwen3-VL-30B-A3B-Instruct-abliteratedRatio
4,0960.25 GiB0.38 GiB1.50×
8,1920.50 GiB0.75 GiB1.50×
16,3841.00 GiB1.50 GiB1.50×
32,7682.00 GiB3.00 GiB1.50×
65,5364.00 GiB6.00 GiB1.50×
131,0728.00 GiB12.00 GiB1.50×