Model comparison

Tinman-gemma4-companion-merged vs Qwen3.8-27B

At Q4_K_M, Tinman-gemma4-companion-merged is the smaller download — 5,302,272,544 bytes against 16,810,714,336. At long context the gap widens: Tinman-gemma4-companion-merged's KV cache at 32K is 4.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Tinman-gemma4-companion-mergedQwen3.8-27B
Parameters7.9B27.8B
Architecturegemma4qwen35
Layers4264
Native context131,072262,144
Mixture of expertsnono
Quantizations published322
Smallest quantization4.94 GiB8.39 GiB
Q4_K_M4.94 GiB15.66 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextTinman-gemma4-companion-mergedQwen3.8-27BRatio
4,0960.12 GiB0.25 GiB2.03×
8,1920.18 GiB0.50 GiB2.81×
16,3840.29 GiB1.00 GiB3.48×
32,7680.51 GiB2.00 GiB3.95×
65,5360.94 GiB4.00 GiB4.24×
131,0721.82 GiB8.00 GiB4.40×