Model comparison

Skywork-R1V3-38B vs gemma-4-26B-A4B-it

At Q4_K_M, gemma-4-26B-A4B-it is the smaller download — 16,796,017,248 bytes against 19,848,566,240.

From the file· summed bytes, KV per layer

Side by side

Skywork-R1V3-38Bgemma-4-26B-A4B-it
Parameters38.4B26.5B
Architectureqwen2gemma4
Layers30
Native context262,144
Mixture of expertsnoyes, 128 experts
Quantizations published3046
Smallest quantization8.41 GiB8.99 GiB
Q4_K_M18.49 GiB15.64 GiB
Licencemitapache-2.0

KV cache by context

the term that decides long-context viability
ContextSkywork-R1V3-38Bgemma-4-26B-A4B-itRatio
4,0960.45 GiB
8,1920.61 GiB
16,3840.92 GiB
32,7681.54 GiB
65,5362.79 GiB
131,0725.29 GiB