Model comparison

gemma-4-26B-A4B-it vs InternVL3_5-14B

At Q4_K_M, InternVL3_5-14B is the smaller download — 9,001,749,952 bytes against 16,796,017,248.

From the file· summed bytes, KV per layer

Side by side

gemma-4-26B-A4B-itInternVL3_5-14B
Parameters26.5B15.1B
Architecturegemma4qwen3
Layers30
Native context262,144
Mixture of expertsyes, 128 expertsno
Quantizations published4628
Smallest quantization8.99 GiB4.62 GiB
Q4_K_M15.64 GiB8.38 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
Contextgemma-4-26B-A4B-itInternVL3_5-14BRatio
4,0960.45 GiB
8,1920.61 GiB
16,3840.92 GiB
32,7681.54 GiB
65,5362.79 GiB
131,0725.29 GiB