Is Llama-3.2-3B-Instruct-heretic-ablitered-uncensored or Qwen3-4B smaller?

Llama-3.2-3B-Instruct-heretic-ablitered-uncensored is smaller at Q4_K_M: 1.88 GiB against 2.33 GiB.

Which uses less memory at long context?

Llama-3.2-3B-Instruct-heretic-ablitered-uncensored — its KV cache at 32K context is 1.3x smaller, because of how its attention layers cache.

Model comparison

Llama-3.2-3B-Instruct-heretic-ablitered-uncensored vs Qwen3-4B

At Q4_K_M, Llama-3.2-3B-Instruct-heretic-ablitered-uncensored is the smaller download — 2,019,377,920 bytes against 2,497,280,256. At long context the gap widens: Llama-3.2-3B-Instruct-heretic-ablitered-uncensored'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-heretic-ablitered-uncensored	Qwen3-4B
Parameters	3.2B	4.0B
Architecture	llama	qwen3
Layers	28	36
Native context	131,072	40,960
Mixture of experts	no	no
Quantizations published	36	29
Smallest quantization	0.81 GiB	1.01 GiB
Q4_K_M	1.88 GiB	2.33 GiB
Licence	—	—

KV cache by context

the term that decides long-context viability

Context	Llama-3.2-3B-Instruct-heretic-ablitered-uncensored	Qwen3-4B	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×