Model comparison

SmolVLM-Instruct vs HyperCLOVAX-SEED-Text-Instruct-1.5B

At Q4_K_M, SmolVLM-Instruct is the smaller download — 1,112,242,368 bytes against 1,133,974,368.

From the file· summed bytes, KV per layer

Side by side

SmolVLM-InstructHyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters2.2B1.6B
Architecturellamallama
Layers24
Native context16,384
Mixture of expertsnono
Quantizations published31
Smallest quantization1.04 GiB1.06 GiB
Q4_K_M1.04 GiB1.06 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
ContextSmolVLM-InstructHyperCLOVAX-SEED-Text-Instruct-1.5BRatio
4,0960.75 GiB
8,1921.50 GiB
16,3843.00 GiB
32,7686.00 GiB
65,53612.00 GiB
131,07224.00 GiB