Model comparison

Llama-3.1-8B-Instruct-abliterated vs Qwen3-Coder-30B-A3B-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

Llama-3.1-8B-Instruct-abliteratedQwen3-Coder-30B-A3B-Instruct
Parameters8.0B30.5B
Architecturellamaqwen3moe
Layers48
Native context262,144
Mixture of expertsnoyes, 128 experts
Quantizations published246
Smallest quantization5.34 GiB7.46 GiB
Q4_K_M17.28 GiB
Licenceotherapache-2.0

KV cache by context

the term that decides long-context viability
ContextLlama-3.1-8B-Instruct-abliteratedQwen3-Coder-30B-A3B-InstructRatio
4,0960.38 GiB
8,1920.75 GiB
16,3841.50 GiB
32,7683.00 GiB
65,5366.00 GiB
131,07212.00 GiB