Is Phi-4-reasoning-plus or Qwen3-8B smaller?

Qwen3-8B is smaller at Q4_K_M: 4.68 GiB against 8.43 GiB.

Which uses less memory at long context?

Qwen3-8B — its KV cache at 32K context is 1.4x smaller, because of how its attention layers cache.

Model comparison

Phi-4-reasoning-plus vs Qwen3-8B

At Q4_K_M, Qwen3-8B is the smaller download — 5,027,783,488 bytes against 9,053,116,128. At long context the gap widens: Qwen3-8B's KV cache at 32K is 1.4× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Phi-4-reasoning-plus	Qwen3-8B
Parameters	14.7B	8.2B
Architecture	phi3	qwen3
Layers	40	36
Native context	32,768	40,960
Mixture of experts	no	no
Quantizations published	46	51
Smallest quantization	3.33 GiB	2.12 GiB
Q4_K_M	8.43 GiB	4.68 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Phi-4-reasoning-plus	Qwen3-8B	Ratio
4,096	0.78 GiB	0.56 GiB	1.39×
8,192	1.56 GiB	1.13 GiB	1.39×
16,384	3.13 GiB	2.25 GiB	1.39×
32,768	6.25 GiB	4.50 GiB	1.39×
65,536	12.50 GiB	9.00 GiB	1.39×
131,072	25.00 GiB	18.00 GiB	1.39×