Model comparison

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP vs Ministral-3-8B-Reasoning-2512-heretic

At Q4_K_M, Ministral-3-8B-Reasoning-2512-heretic is the smaller download — 5,198,385,440 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 2.1× 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-MTPMinistral-3-8B-Reasoning-2512-heretic
Parameters27.8B8.9B
Architectureqwen35mistral3
Layers6434
Native context262,144262,144
Mixture of expertsnono
Quantizations published343
Smallest quantization10.12 GiB4.84 GiB
Q4_K_M34.04 GiB4.84 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTPMinistral-3-8B-Reasoning-2512-hereticRatio
4,0960.25 GiB0.53 GiB2.12×
8,1920.50 GiB1.06 GiB2.12×
16,3841.00 GiB2.13 GiB2.12×
32,7682.00 GiB4.25 GiB2.12×
65,5364.00 GiB8.50 GiB2.12×
131,0728.00 GiB17.00 GiB2.12×