Model comparison

polyglot-lion-1.7b vs gemma-3-1b-it

At Q4_K_M, gemma-3-1b-it is the smaller download — 806,058,240 bytes against 1,107,408,160.

From the file· summed bytes, KV per layer

Side by side

polyglot-lion-1.7bgemma-3-1b-it
Parameters2.0B1000M
Architectureqwen3vlgemma3
Layers26
Native context32,768
Mixture of expertsnono
Quantizations published3628
Smallest quantization0.48 GiB0.52 GiB
Q4_K_M1.03 GiB0.75 GiB
Licencemitgemma

KV cache by context

the term that decides long-context viability
Contextpolyglot-lion-1.7bgemma-3-1b-itRatio
4,0960.04 GiB
8,1920.05 GiB
16,3840.08 GiB
32,7680.15 GiB
65,5360.27 GiB
131,0720.52 GiB