Model comparison

gemma-4-E2B-it-abliterated 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 3,427,874,208.

From the file· summed bytes, KV per layer

Side by side

gemma-4-E2B-it-abliteratedHyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters5.1B1.6B
Architecturegemma4llama
Layers35
Native context131,072
Mixture of expertsnono
Quantizations published361
Smallest quantization2.16 GiB1.06 GiB
Q4_K_M3.19 GiB1.06 GiB
Licencegemmaother

KV cache by context

the term that decides long-context viability
Contextgemma-4-E2B-it-abliteratedHyperCLOVAX-SEED-Text-Instruct-1.5BRatio
4,0960.05 GiB
8,1920.08 GiB
16,3840.14 GiB
32,7680.25 GiB
65,5360.46 GiB
131,0720.90 GiB