Is llama-3.2-3b-instruct-bnb-4bit or Qwen3-8B smaller?

llama-3.2-3b-instruct-bnb-4bit is smaller at Q4_K_M: 1.88 GiB against 4.68 GiB.

Which uses less memory at long context?

llama-3.2-3b-instruct-bnb-4bit — its KV cache at 32K context is 1.3x smaller, because of how its attention layers cache.

Model comparison

llama-3.2-3b-instruct-bnb-4bit vs Qwen3-8B

At Q4_K_M, llama-3.2-3b-instruct-bnb-4bit is the smaller download — 2,019,377,184 bytes against 5,027,783,488. At long context the gap widens: llama-3.2-3b-instruct-bnb-4bit's KV cache at 32K is 1.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	llama-3.2-3b-instruct-bnb-4bit	Qwen3-8B
Parameters	3.3B	8.2B
Architecture	llama	qwen3
Layers	28	36
Native context	131,072	40,960
Mixture of experts	no	no
Quantizations published	16	51
Smallest quantization	1.27 GiB	2.12 GiB
Q4_K_M	1.88 GiB	4.68 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	llama-3.2-3b-instruct-bnb-4bit	Qwen3-8B	Ratio
4,096	0.44 GiB	0.56 GiB	1.29×
8,192	0.88 GiB	1.13 GiB	1.29×
16,384	1.75 GiB	2.25 GiB	1.29×
32,768	3.50 GiB	4.50 GiB	1.29×
65,536	7.00 GiB	9.00 GiB	1.29×
131,072	14.00 GiB	18.00 GiB	1.29×