Model comparison

ThinkingCap-Qwen3.6-27B vs gemma-4-26B-A4B-it

At Q4_K_M, gemma-4-26B-A4B-it is the smaller download — 16,796,017,248 bytes against 16,810,713,056. At long context the gap widens: gemma-4-26B-A4B-it's KV cache at 32K is 1.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

ThinkingCap-Qwen3.6-27Bgemma-4-26B-A4B-it
Parameters27.4B26.5B
Architectureqwen35gemma4
Layers6430
Native context262,144262,144
Mixture of expertsnoyes, 128 experts
Quantizations published2846
Smallest quantization9.30 GiB8.99 GiB
Q4_K_M15.66 GiB15.64 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
ContextThinkingCap-Qwen3.6-27Bgemma-4-26B-A4B-itRatio
4,0960.25 GiB0.45 GiB1.80×
8,1920.50 GiB0.61 GiB1.21×
16,3841.00 GiB0.92 GiB1.09×
32,7682.00 GiB1.54 GiB1.30×
65,5364.00 GiB2.79 GiB1.43×
131,0728.00 GiB5.29 GiB1.51×