Is Supertron2-Reranker-2B or Llama-3.2-1B-Instruct smaller?

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

Which uses less memory at long context?

Llama-3.2-1B-Instruct — its KV cache at 32K context is 3.5x smaller, because of how its attention layers cache.

Model comparison

Supertron2-Reranker-2B 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: Llama-3.2-1B-Instruct's KV cache at 32K is 3.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Supertron2-Reranker-2B	Llama-3.2-1B-Instruct
Parameters	2.1B	1.2B
Architecture	qwen3vl	llama
Layers	28	16
Native context	262,144	131,072
Mixture of experts	no	no
Quantizations published	24	39
Smallest quantization	0.48 GiB	0.39 GiB
Q4_K_M	—	0.75 GiB
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	Supertron2-Reranker-2B	Llama-3.2-1B-Instruct	Ratio
4,096	0.44 GiB	0.13 GiB	3.50×
8,192	0.88 GiB	0.25 GiB	3.50×
16,384	1.75 GiB	0.50 GiB	3.50×
32,768	3.50 GiB	1.00 GiB	3.50×
65,536	7.00 GiB	2.00 GiB	3.50×
131,072	14.00 GiB	4.00 GiB	3.50×