Model comparison

gemma-4-26B-A4B-it vs glm-4v-9b

At Q4_K_M, glm-4v-9b is the smaller download — 6,166,574,560 bytes against 16,796,017,248.

From the file· summed bytes, KV per layer

Side by side

gemma-4-26B-A4B-itglm-4v-9b
Parameters26.5B13.9B
Architecturegemma4glm4
Layers30
Native context262,144
Mixture of expertsyes, 128 expertsno
Quantizations published4614
Smallest quantization8.99 GiB3.73 GiB
Q4_K_M15.64 GiB5.74 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
Contextgemma-4-26B-A4B-itglm-4v-9bRatio
4,0960.45 GiB
8,1920.61 GiB
16,3840.92 GiB
32,7681.54 GiB
65,5362.79 GiB
131,0725.29 GiB