Model comparison

FableForge-1.5B-v2 vs gemma-3-1b-it

At Q4_K_M, gemma-3-1b-it is the smaller download — 806,058,240 bytes against 986,047,904.

From the file· summed bytes, KV per layer

Side by side

FableForge-1.5B-v2gemma-3-1b-it
Parameters1.5B1000M
Architectureqwen2gemma3
Layers26
Native context32,768
Mixture of expertsnono
Quantizations published2328
Smallest quantization0.41 GiB0.52 GiB
Q4_K_M0.92 GiB0.75 GiB
Licenceapache-2.0gemma

KV cache by context

the term that decides long-context viability
ContextFableForge-1.5B-v2gemma-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