Model comparison

MR_MARTIN_31b_V1.0_Gemma-4-base-ftp vs Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

MR_MARTIN_31b_V1.0_Gemma-4-base-ftpQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP
Parameters30.7B27.8B
Architecturegemma4qwen35
Layers64
Native context262,144
Mixture of expertsnono
Quantizations published2334
Smallest quantization6.66 GiB10.12 GiB
Q4_K_M34.04 GiB
Licenceotherapache-2.0

KV cache by context

the term that decides long-context viability
ContextMR_MARTIN_31b_V1.0_Gemma-4-base-ftpQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTPRatio
4,0960.25 GiB
8,1920.50 GiB
16,3841.00 GiB
32,7682.00 GiB
65,5364.00 GiB
131,0728.00 GiB