Model comparison

spoomplesmaxx-v2.1-30B vs gpt-oss-20b

At Q4_K_M, gpt-oss-20b is the smaller download — 11,624,759,488 bytes against 17,490,242,528. At long context the gap widens: gpt-oss-20b's KV cache at 32K is 10.4× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

spoomplesmaxx-v2.1-30Bgpt-oss-20b
Parameters28.9B21.5B
Architecturegranitegpt-oss
Layers6424
Native context131,072131,072
Mixture of expertsnoyes, 32 experts
Quantizations published3415
Smallest quantization5.73 GiB10.68 GiB
Q4_K_M16.29 GiB10.83 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
Contextspoomplesmaxx-v2.1-30Bgpt-oss-20bRatio
4,0961.00 GiB0.11 GiB8.98×
8,1922.00 GiB0.21 GiB9.75×
16,3844.00 GiB0.39 GiB10.19×
32,7688.00 GiB0.77 GiB10.42×
65,53616.00 GiB1.52 GiB10.54×
131,07232.00 GiB3.02 GiB10.60×