Model comparison

gemma-4-26B-A4B-it vs supergemma4-26b-abliterated-multimodal

At Q4_K_M, supergemma4-26b-abliterated-multimodal is the smaller download — 16,796,016,032 bytes against 16,796,017,248.

From the file· summed bytes, KV per layer

Side by side

gemma-4-26B-A4B-itsupergemma4-26b-abliterated-multimodal
Parameters26.5B25.8B
Architecturegemma4gemma4
Layers3030
Native context262,144262,144
Mixture of expertsyes, 128 expertsyes, 128 experts
Quantizations published461
Smallest quantization8.99 GiB15.64 GiB
Q4_K_M15.64 GiB15.64 GiB
Licenceapache-2.0gemma

KV cache by context

the term that decides long-context viability
Contextgemma-4-26B-A4B-itsupergemma4-26b-abliterated-multimodalRatio
4,0960.45 GiB0.45 GiB1.00×
8,1920.61 GiB0.61 GiB1.00×
16,3840.92 GiB0.92 GiB1.00×
32,7681.54 GiB1.54 GiB1.00×
65,5362.79 GiB2.79 GiB1.00×
131,0725.29 GiB5.29 GiB1.00×
gemma-4-26B-A4B-it vs supergemma4-26b-abliterated-multimodal — size, memory and hardware fit — ossmodeldb