Is Llama-3.2-3B-Instruct-uncensored or gemma-4-E4B-it smaller?

Llama-3.2-3B-Instruct-uncensored is smaller at Q4_K_M: 2.09 GiB against 4.64 GiB.

Which uses less memory at long context?

gemma-4-E4B-it — its KV cache at 32K context is 6.9x smaller, because of how its attention layers cache.

Model comparison

Llama-3.2-3B-Instruct-uncensored vs gemma-4-E4B-it

At Q4_K_M, Llama-3.2-3B-Instruct-uncensored is the smaller download — 2,241,003,904 bytes against 4,977,171,584. At long context the gap widens: gemma-4-E4B-it's KV cache at 32K is 6.9× 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-uncensored	gemma-4-E4B-it
Parameters	3.6B	8.0B
Architecture	llama	gemma4
Layers	28	42
Native context	131,072	131,072
Mixture of experts	no	no
Quantizations published	35	36
Smallest quantization	1.39 GiB	3.30 GiB
Q4_K_M	2.09 GiB	4.64 GiB
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Llama-3.2-3B-Instruct-uncensored	gemma-4-E4B-it	Ratio
4,096	0.44 GiB	0.12 GiB	3.56×
8,192	0.88 GiB	0.18 GiB	4.92×
16,384	1.75 GiB	0.29 GiB	6.10×
32,768	3.50 GiB	0.51 GiB	6.92×
65,536	7.00 GiB	0.94 GiB	7.42×
131,072	14.00 GiB	1.82 GiB	7.70×