Model comparison

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

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

Qwen3.6-35B-A3Bgemma-3-27b-it-qat-q4_0-unquantized
Parameters36.0B27.4B
Architectureqwen35moegemma3
Layers40
Native context262,144
Mixture of expertsyes, 256 expertsno
Quantizations published6145
Smallest quantization8.77 GiB6.06 GiB
Q4_K_M19.71 GiB15.41 GiB
Licenceapache-2.0gemma

KV cache by context

the term that decides long-context viability
ContextQwen3.6-35B-A3Bgemma-3-27b-it-qat-q4_0-unquantizedRatio
4,0960.08 GiB
8,1920.16 GiB
16,3840.31 GiB
32,7680.63 GiB
65,5361.25 GiB
131,0722.50 GiB