Is Huihui-Qwen3.5-0.8B-abliterated-Athanorlite-ORPO or Llama-3.2-1B-Instruct smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

Huihui-Qwen3.5-0.8B-abliterated-Athanorlite-ORPO — its KV cache at 32K context is 2.7x smaller, because of how its attention layers cache.

Model comparison

Huihui-Qwen3.5-0.8B-abliterated-Athanorlite-ORPO vs Llama-3.2-1B-Instruct

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Huihui-Qwen3.5-0.8B-abliterated-Athanorlite-ORPO's KV cache at 32K is 2.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Huihui-Qwen3.5-0.8B-abliterated-Athanorlite-ORPO	Llama-3.2-1B-Instruct
Parameters	853M	1.2B
Architecture	qwen35	llama
Layers	24	16
Native context	262,144	131,072
Mixture of experts	no	no
Quantizations published	24	39
Smallest quantization	0.31 GiB	0.39 GiB
Q4_K_M	—	0.75 GiB
Licence	—	—

KV cache by context

the term that decides long-context viability

Context	Huihui-Qwen3.5-0.8B-abliterated-Athanorlite-ORPO	Llama-3.2-1B-Instruct	Ratio
4,096	0.05 GiB	0.13 GiB	2.66×
8,192	0.09 GiB	0.25 GiB	2.67×
16,384	0.19 GiB	0.50 GiB	2.67×
32,768	0.38 GiB	1.00 GiB	2.67×
65,536	0.75 GiB	2.00 GiB	2.67×
131,072	1.50 GiB	4.00 GiB	2.67×