Model comparison

Fallen-Gemma3-27B-v1 vs Qwen3-30B-A3B-Thinking-2507

At Q4_K_M, Fallen-Gemma3-27B-v1 is the smaller download — 16,546,688,704 bytes against 18,556,685,824. At long context the gap widens: Fallen-Gemma3-27B-v1'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

Fallen-Gemma3-27B-v1Qwen3-30B-A3B-Thinking-2507
Parameters27.4B30.5B
Architecturegemma3qwen3moe
Layers4848
Native context262,144
Mixture of expertsnoyes, 128 experts
Quantizations published2551
Smallest quantization7.86 GiB7.05 GiB
Q4_K_M15.41 GiB17.28 GiB
Licenceotherapache-2.0

KV cache by context

the term that decides long-context viability
ContextFallen-Gemma3-27B-v1Qwen3-30B-A3B-Thinking-2507Ratio
4,0960.67 GiB0.38 GiB1.80×
8,1920.91 GiB0.75 GiB1.21×
16,3841.38 GiB1.50 GiB1.09×
32,7682.31 GiB3.00 GiB1.30×
65,5364.19 GiB6.00 GiB1.43×
131,0727.94 GiB12.00 GiB1.51×