Model comparison

DA3-BASE vs Llama-3.1-8B-Instruct

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

DA3-BASELlama-3.1-8B-Instruct
Parameters8.0B
Architecturedepthanything3llama
Layers32
Native context131,072
Mixture of expertsnono
Quantizations published645
Smallest quantization1.31 GiB2.02 GiB
Q4_K_M4.58 GiB
Licenceapache-2.0llama3.1

KV cache by context

the term that decides long-context viability
ContextDA3-BASELlama-3.1-8B-InstructRatio
4,0960.50 GiB
8,1921.00 GiB
16,3842.00 GiB
32,7684.00 GiB
65,5368.00 GiB
131,07216.00 GiB