Model comparison

INTELLECT-1-Instruct vs HyperCLOVAX-SEED-Text-Instruct-1.5B

At Q4_K_M, HyperCLOVAX-SEED-Text-Instruct-1.5B is the smaller download — 1,133,974,368 bytes against 6,229,006,784.

From the file· summed bytes, KV per layer

Side by side

INTELLECT-1-InstructHyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters10.2B1.6B
Architecturellamallama
Layers42
Native context8,192
Mixture of expertsnono
Quantizations published531
Smallest quantization2.31 GiB1.06 GiB
Q4_K_M5.80 GiB1.06 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
ContextINTELLECT-1-InstructHyperCLOVAX-SEED-Text-Instruct-1.5BRatio
4,0960.66 GiB
8,1921.31 GiB
16,3842.63 GiB
32,7685.25 GiB
65,53610.50 GiB
131,07221.00 GiB