Model comparison

madlad400-3b-mt vs Qwen3-4B

At Q4_K_M, madlad400-3b-mt is the smaller download — 1,858,124,864 bytes against 2,497,280,256.

From the file· summed bytes, KV per layer

Side by side

madlad400-3b-mtQwen3-4B
Parameters2.9B4.0B
Architecturet5qwen3
Layers36
Native context40,960
Mixture of expertsnono
Quantizations published529
Smallest quantization1.73 GiB1.01 GiB
Q4_K_M1.73 GiB2.33 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
Contextmadlad400-3b-mtQwen3-4BRatio
4,0960.56 GiB
8,1921.13 GiB
16,3842.25 GiB
32,7684.50 GiB
65,5369.00 GiB
131,07218.00 GiB