Model comparison

Marco-Nano-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 5,371,989,536.

From the file· summed bytes, KV per layer

Side by side

Marco-Nano-InstructHyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters8.0B1.6B
Architectureqwen3moellama
Layers28
Native context32,768
Mixture of expertsyes, 232 expertsno
Quantizations published361
Smallest quantization2.44 GiB1.06 GiB
Q4_K_M5.00 GiB1.06 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
ContextMarco-Nano-InstructHyperCLOVAX-SEED-Text-Instruct-1.5BRatio
4,0960.44 GiB
8,1920.88 GiB
16,3841.75 GiB
32,7683.50 GiB
65,5367.00 GiB
131,07214.00 GiB