Model comparison

dolphincoder-starcoder2-15b vs Qwen3-8B

At Q4_K_M, Qwen3-8B is the smaller download — 5,027,783,488 bytes against 9,860,206,880.

From the file· summed bytes, KV per layer

Side by side

dolphincoder-starcoder2-15bQwen3-8B
Parameters16.0B8.2B
Architecturestarcoder2qwen3
Layers4036
Native context16,38440,960
Mixture of expertsnono
Quantizations published3551
Smallest quantization3.31 GiB2.12 GiB
Q4_K_M9.18 GiB4.68 GiB
Licencebigcode-openrail-mapache-2.0

KV cache by context

the term that decides long-context viability
Contextdolphincoder-starcoder2-15bQwen3-8BRatio
4,0960.56 GiB
8,1921.13 GiB
16,3842.25 GiB
32,7684.50 GiB
65,5369.00 GiB
131,07218.00 GiB