Is deepseek-coder-5.7bmqa-base or Qwen3-4B smaller?

Qwen3-4B is smaller at Q4_K_M: 2.33 GiB against 3.20 GiB.

Which uses less memory at long context?

deepseek-coder-5.7bmqa-base — its KV cache at 32K context is 9.0x smaller, because of how its attention layers cache.

Model comparison

deepseek-coder-5.7bmqa-base vs Qwen3-4B

At Q4_K_M, Qwen3-4B is the smaller download — 2,497,280,256 bytes against 3,430,867,168. At long context the gap widens: deepseek-coder-5.7bmqa-base's KV cache at 32K is 9.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	deepseek-coder-5.7bmqa-base	Qwen3-4B
Parameters	5.7B	4.0B
Architecture	llama	qwen3
Layers	32	36
Native context	16,384	40,960
Mixture of experts	no	no
Quantizations published	14	29
Smallest quantization	2.00 GiB	1.01 GiB
Q4_K_M	3.20 GiB	2.33 GiB
Licence	other	—

KV cache by context

the term that decides long-context viability

Context	deepseek-coder-5.7bmqa-base	Qwen3-4B	Ratio
4,096	0.06 GiB	0.56 GiB	9.00×
8,192	0.13 GiB	1.13 GiB	9.00×
16,384	0.25 GiB	2.25 GiB	9.00×
32,768	0.50 GiB	4.50 GiB	9.00×
65,536	1.00 GiB	9.00 GiB	9.00×
131,072	2.00 GiB	18.00 GiB	9.00×