Model comparison

Supertron2-Reranker-2B vs HyperCLOVAX-SEED-Text-Instruct-1.5B

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

Supertron2-Reranker-2BHyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters2.1B1.6B
Architectureqwen3vlllama
Layers28
Native context262,144
Mixture of expertsnono
Quantizations published241
Smallest quantization0.48 GiB1.06 GiB
Q4_K_M1.06 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
ContextSupertron2-Reranker-2BHyperCLOVAX-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