Model comparison

OpenCoder-1.5B-Instruct vs Qwen3-VL-8B-Instruct-abliterated-v1

At Q4_K_M, OpenCoder-1.5B-Instruct is the smaller download — 1,417,775,200 bytes against 5,027,785,792.

From the file· summed bytes, KV per layer

Side by side

OpenCoder-1.5B-InstructQwen3-VL-8B-Instruct-abliterated-v1
Parameters1.9B8.8B
Architecturellamaqwen3vl
Layers24
Native context4,096
Mixture of expertsnono
Quantizations published448
Smallest quantization1.18 GiB1.97 GiB
Q4_K_M1.32 GiB4.68 GiB
Licenceotherapache-2.0

KV cache by context

the term that decides long-context viability
ContextOpenCoder-1.5B-InstructQwen3-VL-8B-Instruct-abliterated-v1Ratio
4,0960.82 GiB
8,1921.64 GiB
16,3843.28 GiB
32,7686.56 GiB
65,53613.13 GiB
131,07226.25 GiB