Model comparison

gemma-4-26B-A4B-it vs Qwythos-9B-Claude-Mythos-5-1M

At Q4_K_M, Qwythos-9B-Claude-Mythos-5-1M is the smaller download — 11,516,776,704 bytes against 16,796,017,248. At long context the gap widens: Qwythos-9B-Claude-Mythos-5-1M's KV cache at 32K is 1.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

gemma-4-26B-A4B-itQwythos-9B-Claude-Mythos-5-1M
Parameters26.5B9.4B
Architecturegemma4qwen35
Layers3032
Native context262,1441,048,576
Mixture of expertsyes, 128 expertsno
Quantizations published4616
Smallest quantization8.99 GiB5.38 GiB
Q4_K_M15.64 GiB10.73 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
Contextgemma-4-26B-A4B-itQwythos-9B-Claude-Mythos-5-1MRatio
4,0960.45 GiB0.13 GiB3.59×
8,1920.61 GiB0.25 GiB2.42×
16,3840.92 GiB0.50 GiB1.84×
32,7681.54 GiB1.00 GiB1.54×
65,5362.79 GiB2.00 GiB1.40×
131,0725.29 GiB4.00 GiB1.32×