Is PiCo-1B or Qwen3-4B smaller?

PiCo-1B is smaller at Q4_K_M: 0.92 GiB against 2.33 GiB.

Which uses less memory at long context?

PiCo-1B — its KV cache at 32K context is 5.1x smaller, because of how its attention layers cache.

Model comparison

PiCo-1B vs Qwen3-4B

At Q4_K_M, PiCo-1B is the smaller download — 986,048,224 bytes against 2,497,280,256. At long context the gap widens: PiCo-1B's KV cache at 32K is 5.1× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	PiCo-1B	Qwen3-4B
Parameters	1.5B	4.0B
Architecture	qwen2	qwen3
Layers	28	36
Native context	131,072	40,960
Mixture of experts	no	no
Quantizations published	36	29
Smallest quantization	0.41 GiB	1.01 GiB
Q4_K_M	0.92 GiB	2.33 GiB
Licence	openrail	—

KV cache by context

the term that decides long-context viability

Context	PiCo-1B	Qwen3-4B	Ratio
4,096	0.11 GiB	0.56 GiB	5.14×
8,192	0.22 GiB	1.13 GiB	5.14×
16,384	0.44 GiB	2.25 GiB	5.14×
32,768	0.88 GiB	4.50 GiB	5.14×
65,536	1.75 GiB	9.00 GiB	5.14×
131,072	3.50 GiB	18.00 GiB	5.14×