Model comparison

Chimera-X-26B-A4B vs Qwen3.8-27B

At Q4_K_M, Qwen3.8-27B is the smaller download — 16,810,714,336 bytes against 17,211,252,736. At long context the gap widens: Chimera-X-26B-A4B'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

Chimera-X-26B-A4BQwen3.8-27B
Parameters26.5B27.8B
Architecturegemma4qwen35
Layers3064
Native context262,144262,144
Mixture of expertsyes, 128 expertsno
Quantizations published3422
Smallest quantization7.95 GiB8.39 GiB
Q4_K_M16.03 GiB15.66 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextChimera-X-26B-A4BQwen3.8-27BRatio
4,0960.45 GiB0.25 GiB1.80×
8,1920.61 GiB0.50 GiB1.21×
16,3840.92 GiB1.00 GiB1.09×
32,7681.54 GiB2.00 GiB1.30×
65,5362.79 GiB4.00 GiB1.43×
131,0725.29 GiB8.00 GiB1.51×