Model comparison

Sulphur-2-base vs MiniMax-H3

At Q4_K_M, Sulphur-2-base is the smaller download — 5,629,108,608 bytes against 14,576,977,960.

From the file· summed bytes, KV per layer

Side by side

Sulphur-2-baseMiniMax-H3
Parameters9.2B33.1B
Architectureltxvqwen3vl
Layers
Native context
Mixture of expertsnono
Quantizations published1322
Smallest quantization5.07 GiB10.60 GiB
Q4_K_M5.24 GiB13.58 GiB
Licenceother

KV cache by context

the term that decides long-context viability
ContextSulphur-2-baseMiniMax-H3Ratio
4,096
8,192
16,384
32,768
65,536
131,072