Is deepseek-coder-33b-base or Qwen3.6-27B smaller?

Qwen3.6-27B is smaller at Q4_K_M: 15.41 GiB against 18.57 GiB.

Which uses less memory at long context?

Qwen3.6-27B — its KV cache at 32K context is 3.9x smaller, because of how its attention layers cache.

Model comparison

deepseek-coder-33b-base vs Qwen3.6-27B

At Q4_K_M, Qwen3.6-27B is the smaller download — 16,547,397,888 bytes against 19,940,659,168. At long context the gap widens: Qwen3.6-27B's KV cache at 32K is 3.9× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	deepseek-coder-33b-base	Qwen3.6-27B
Parameters	33.3B	27.8B
Architecture	llama	qwen35
Layers	62	64
Native context	16,384	262,144
Mixture of experts	no	no
Quantizations published	12	40
Smallest quantization	13.07 GiB	8.74 GiB
Q4_K_M	18.57 GiB	15.41 GiB
Licence	other	apache-2.0

KV cache by context

the term that decides long-context viability

Context	deepseek-coder-33b-base	Qwen3.6-27B	Ratio
4,096	0.97 GiB	0.25 GiB	3.87×
8,192	1.94 GiB	0.50 GiB	3.87×
16,384	3.88 GiB	1.00 GiB	3.87×
32,768	7.75 GiB	2.00 GiB	3.87×
65,536	15.50 GiB	4.00 GiB	3.87×
131,072	31.00 GiB	8.00 GiB	3.87×