Model comparison

reasoning-summarizer-800m-pre vs HyperCLOVAX-SEED-Text-Instruct-1.5B

At Q4_K_M, reasoning-summarizer-800m-pre is the smaller download — 529,289,792 bytes against 1,133,974,368.

From the file· summed bytes, KV per layer

Side by side

reasoning-summarizer-800m-preHyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters752M1.6B
Architectureqwen35llama
Layers24
Native context262,144
Mixture of expertsnono
Quantizations published61
Smallest quantization0.47 GiB1.06 GiB
Q4_K_M0.49 GiB1.06 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
Contextreasoning-summarizer-800m-preHyperCLOVAX-SEED-Text-Instruct-1.5BRatio
4,0960.05 GiB
8,1920.09 GiB
16,3840.19 GiB
32,7680.38 GiB
65,5360.75 GiB
131,0721.50 GiB