Model comparison

Hemlock-Qwopus3.5-9B-Coder vs Qwythos-9B-Claude-Mythos-5-1M

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

Hemlock-Qwopus3.5-9B-CoderQwythos-9B-Claude-Mythos-5-1M
Parameters9.7B9.4B
Architectureqwen35qwen35
Layers3232
Native context262,1441,048,576
Mixture of expertsnono
Quantizations published1516
Smallest quantization3.65 GiB5.38 GiB
Q4_K_M10.73 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
ContextHemlock-Qwopus3.5-9B-CoderQwythos-9B-Claude-Mythos-5-1MRatio
4,0960.13 GiB0.13 GiB1.00×
8,1920.25 GiB0.25 GiB1.00×
16,3840.50 GiB0.50 GiB1.00×
32,7681.00 GiB1.00 GiB1.00×
65,5362.00 GiB2.00 GiB1.00×
131,0724.00 GiB4.00 GiB1.00×