Model comparison

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP vs Tiger-Gemma-12B-v3

At Q4_K_M, Tiger-Gemma-12B-v3 is the smaller download — 7,867,147,904 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 1.2× 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-MTPTiger-Gemma-12B-v3
Parameters27.8B12.8B
Architectureqwen35gemma3
Layers6448
Native context262,144131,072
Mixture of expertsnono
Quantizations published3424
Smallest quantization10.12 GiB4.15 GiB
Q4_K_M34.04 GiB7.33 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-MTPTiger-Gemma-12B-v3Ratio
4,0960.25 GiB0.72 GiB2.87×
8,1920.50 GiB0.97 GiB1.94×
16,3841.00 GiB1.47 GiB1.47×
32,7682.00 GiB2.47 GiB1.23×
65,5364.00 GiB4.47 GiB1.12×
131,0728.00 GiB8.47 GiB1.06×