Model comparison

llava-llama-3-8b-v1_1-transformers vs gemma-4-12B-it

At Q4_K_M, llava-llama-3-8b-v1_1-transformers is the smaller download — 4,921,098,752 bytes against 7,121,861,440.

From the file· summed bytes, KV per layer

Side by side

llava-llama-3-8b-v1_1-transformersgemma-4-12B-it
Parameters8.4B12.0B
Architecturellamagemma4
Layers48
Native context8,192262,144
Mixture of expertsnono
Quantizations published1559
Smallest quantization3.41 GiB3.92 GiB
Q4_K_M4.58 GiB6.63 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
Contextllava-llama-3-8b-v1_1-transformersgemma-4-12B-itRatio
4,0960.72 GiB
8,1920.97 GiB
16,3841.47 GiB
32,7682.47 GiB
65,5364.47 GiB
131,0728.47 GiB