Model comparison

Falcon3-7B-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 4,569,726,368.

From the file· summed bytes, KV per layer

Side by side

Falcon3-7B-InstructHyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters7.5B1.6B
Architecturellamallama
Layers28
Native context32,768
Mixture of expertsnono
Quantizations published301
Smallest quantization2.47 GiB1.06 GiB
Q4_K_M4.26 GiB1.06 GiB
Licenceotherother

KV cache by context

the term that decides long-context viability
ContextFalcon3-7B-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