Model comparison

Qwen-Image-Bench 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 16,547,399,200. At long context the gap widens: Qwythos-9B-Claude-Mythos-5-1M's KV cache at 32K is 2.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Qwen-Image-BenchQwythos-9B-Claude-Mythos-5-1M
Parameters27.4B9.4B
Architectureqwen35qwen35
Layers6432
Native context262,1441,048,576
Mixture of expertsnono
Quantizations published916
Smallest quantization9.98 GiB5.38 GiB
Q4_K_M15.41 GiB10.73 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen-Image-BenchQwythos-9B-Claude-Mythos-5-1MRatio
4,0960.25 GiB0.13 GiB2.00×
8,1920.50 GiB0.25 GiB2.00×
16,3841.00 GiB0.50 GiB2.00×
32,7682.00 GiB1.00 GiB2.00×
65,5364.00 GiB2.00 GiB2.00×
131,0728.00 GiB4.00 GiB2.00×