Model comparison

gemma-3-27b-it-qat-q4_0-unquantized vs Qwen3.6-35B-A3B

At Q4_K_M, gemma-3-27b-it-qat-q4_0-unquantized is the smaller download — 16,546,688,736 bytes against 21,166,757,728.

From the file· summed bytes, KV per layer

Side by side

gemma-3-27b-it-qat-q4_0-unquantizedQwen3.6-35B-A3B
Parameters27.4B36.0B
Architecturegemma3qwen35moe
Layers40
Native context262,144
Mixture of expertsnoyes, 256 experts
Quantizations published4561
Smallest quantization6.06 GiB8.77 GiB
Q4_K_M15.41 GiB19.71 GiB
Licencegemmaapache-2.0

KV cache by context

the term that decides long-context viability
Contextgemma-3-27b-it-qat-q4_0-unquantizedQwen3.6-35B-A3BRatio
4,0960.08 GiB
8,1920.16 GiB
16,3840.31 GiB
32,7680.63 GiB
65,5361.25 GiB
131,0722.50 GiB