Model comparison

Teuken-7B-instruct-research-v0.4 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 5,018,868,320.

From the file· summed bytes, KV per layer

Side by side

Teuken-7B-instruct-research-v0.4HyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters7.5B1.6B
Architecturellamallama
Layers32
Native context4,096
Mixture of expertsnono
Quantizations published411
Smallest quantization2.48 GiB1.06 GiB
Q4_K_M4.67 GiB1.06 GiB
Licenceotherother

KV cache by context

the term that decides long-context viability
ContextTeuken-7B-instruct-research-v0.4HyperCLOVAX-SEED-Text-Instruct-1.5BRatio
4,0960.13 GiB
8,1920.25 GiB
16,3840.50 GiB
32,7681.00 GiB
65,5362.00 GiB
131,0724.00 GiB