Is granite-4.0-350m or Qwen2.5-0.5B-Instruct smaller?

granite-4.0-350m is smaller at Q4_K_M: 0.22 GiB against 0.37 GiB.

Which uses less memory at long context?

Qwen2.5-0.5B-Instruct — its KV cache at 32K context is 2.3x smaller, because of how its attention layers cache.

Model comparison

granite-4.0-350m vs Qwen2.5-0.5B-Instruct

At Q4_K_M, granite-4.0-350m is the smaller download — 236,985,760 bytes against 397,807,936. At long context the gap widens: Qwen2.5-0.5B-Instruct's KV cache at 32K is 2.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	granite-4.0-350m	Qwen2.5-0.5B-Instruct
Parameters	352M	494M
Architecture	granite	qwen2
Layers	28	24
Native context	32,768	32,768
Mixture of experts	no	no
Quantizations published	29	32
Smallest quantization	0.16 GiB	0.31 GiB
Q4_K_M	0.22 GiB	0.37 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	granite-4.0-350m	Qwen2.5-0.5B-Instruct	Ratio
4,096	0.11 GiB	0.05 GiB	2.33×
8,192	0.22 GiB	0.09 GiB	2.33×
16,384	0.44 GiB	0.19 GiB	2.33×
32,768	0.88 GiB	0.38 GiB	2.33×
65,536	1.75 GiB	0.75 GiB	2.33×
131,072	3.50 GiB	1.50 GiB	2.33×