Is OpenCodeReasoning-Nemotron-32B-IOI or Qwen3.8-27B smaller?

Qwen3.8-27B is smaller at Q4_K_M: 15.66 GiB against 18.49 GiB.

Which uses less memory at long context?

Qwen3.8-27B — its KV cache at 32K context is 4.0x smaller, because of how its attention layers cache.

Model comparison

OpenCodeReasoning-Nemotron-32B-IOI vs Qwen3.8-27B

At Q4_K_M, Qwen3.8-27B is the smaller download — 16,810,714,336 bytes against 19,851,336,512. At long context the gap widens: Qwen3.8-27B's KV cache at 32K is 4.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	OpenCodeReasoning-Nemotron-32B-IOI	Qwen3.8-27B
Parameters	32.8B	27.8B
Architecture	qwen2	qwen35
Layers	64	64
Native context	32,768	262,144
Mixture of experts	no	no
Quantizations published	30	22
Smallest quantization	8.41 GiB	8.39 GiB
Q4_K_M	18.49 GiB	15.66 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	OpenCodeReasoning-Nemotron-32B-IOI	Qwen3.8-27B	Ratio
4,096	1.00 GiB	0.25 GiB	4.00×
8,192	2.00 GiB	0.50 GiB	4.00×
16,384	4.00 GiB	1.00 GiB	4.00×
32,768	8.00 GiB	2.00 GiB	4.00×
65,536	16.00 GiB	4.00 GiB	4.00×
131,072	32.00 GiB	8.00 GiB	4.00×