Is Qwen3.8-27B or AReaL-boba-2-32B smaller?

Both publish quantizations; compare the table for the exact sizes.

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

Qwen3.8-27B vs AReaL-boba-2-32B

These two publish different quantization sets; the table below has the exact sizes. 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

	Qwen3.8-27B	AReaL-boba-2-32B
Parameters	27.8B	32.8B
Architecture	qwen35	qwen3
Layers	64	64
Native context	262,144	40,960
Mixture of experts	no	no
Quantizations published	22	23
Smallest quantization	8.39 GiB	6.82 GiB
Q4_K_M	15.66 GiB	—
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.8-27B	AReaL-boba-2-32B	Ratio
4,096	0.25 GiB	1.00 GiB	4.00×
8,192	0.50 GiB	2.00 GiB	4.00×
16,384	1.00 GiB	4.00 GiB	4.00×
32,768	2.00 GiB	8.00 GiB	4.00×
65,536	4.00 GiB	16.00 GiB	4.00×
131,072	8.00 GiB	32.00 GiB	4.00×