Model comparison

antares-1b vs Qwen3-4B

At Q4_K_M, antares-1b is the smaller download — 1,139,251,136 bytes against 2,497,280,256.

From the file· summed bytes, KV per layer

Side by side

antares-1bQwen3-4B
Parameters1.8B4.0B
Architecturegraniteqwen3
Layers36
Native context40,960
Mixture of expertsnono
Quantizations published829
Smallest quantization0.72 GiB1.01 GiB
Q4_K_M1.06 GiB2.33 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
Contextantares-1bQwen3-4BRatio
4,0960.56 GiB
8,1921.13 GiB
16,3842.25 GiB
32,7684.50 GiB
65,5369.00 GiB
131,07218.00 GiB