Model comparison

Qwen3-VL-8B-Instruct-abliterated-v2 vs gemma-4-E2B-it

At Q4_K_M, gemma-4-E2B-it is the smaller download — 3,106,738,272 bytes against 5,027,785,824.

From the file· summed bytes, KV per layer

Side by side

Qwen3-VL-8B-Instruct-abliterated-v2gemma-4-E2B-it
Parameters8.8B5.1B
Architectureqwen3vlgemma4
Layers35
Native context131,072
Mixture of expertsnono
Quantizations published3654
Smallest quantization3.06 GiB2.13 GiB
Q4_K_M4.68 GiB2.89 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3-VL-8B-Instruct-abliterated-v2gemma-4-E2B-itRatio
4,0960.05 GiB
8,1920.08 GiB
16,3840.14 GiB
32,7680.25 GiB
65,5360.46 GiB
131,0720.90 GiB