Is Delphi-25B-SimpleRL-Math or Qwen3.8-27B smaller?

Delphi-25B-SimpleRL-Math is smaller at Q4_K_M: 14.12 GiB against 15.66 GiB.

Which uses less memory at long context?

Qwen3.8-27B — its KV cache at 32K context is 16.7x smaller, because of how its attention layers cache.

Model comparison

Delphi-25B-SimpleRL-Math vs Qwen3.8-27B

At Q4_K_M, Delphi-25B-SimpleRL-Math is the smaller download — 15,160,698,624 bytes against 16,810,714,336. At long context the gap widens: Qwen3.8-27B's KV cache at 32K is 16.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Delphi-25B-SimpleRL-Math	Qwen3.8-27B
Parameters	25.0B	27.8B
Architecture	qwen3	qwen35
Layers	51	64
Native context	16,384	262,144
Mixture of experts	no	no
Quantizations published	34	22
Smallest quantization	5.31 GiB	8.39 GiB
Q4_K_M	14.12 GiB	15.66 GiB
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Delphi-25B-SimpleRL-Math	Qwen3.8-27B	Ratio
4,096	4.18 GiB	0.25 GiB	16.72×
8,192	8.37 GiB	0.50 GiB	16.73×
16,384	16.73 GiB	1.00 GiB	16.73×
32,768	33.47 GiB	2.00 GiB	16.73×
65,536	66.94 GiB	4.00 GiB	16.73×
131,072	133.88 GiB	8.00 GiB	16.73×