Is deepseek-coder-7b-instruct-v1.5 or Qwen3-4B smaller?

Qwen3-4B is smaller at Q4_K_M: 2.33 GiB against 3.93 GiB.

Which uses less memory at long context?

Qwen3-4B — its KV cache at 32K context is 3.3x smaller, because of how its attention layers cache.

Model comparison

deepseek-coder-7b-instruct-v1.5 vs Qwen3-4B

At Q4_K_M, Qwen3-4B is the smaller download — 2,497,280,256 bytes against 4,223,359,872. At long context the gap widens: Qwen3-4B's KV cache at 32K is 3.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	deepseek-coder-7b-instruct-v1.5	Qwen3-4B
Parameters	6.9B	4.0B
Architecture	llama	qwen3
Layers	30	36
Native context	4,096	40,960
Mixture of experts	no	no
Quantizations published	49	29
Smallest quantization	1.61 GiB	1.01 GiB
Q4_K_M	3.93 GiB	2.33 GiB
Licence	other	—

KV cache by context

the term that decides long-context viability

Context	deepseek-coder-7b-instruct-v1.5	Qwen3-4B	Ratio
4,096	1.88 GiB	0.56 GiB	3.33×
8,192	3.75 GiB	1.13 GiB	3.33×
16,384	7.50 GiB	2.25 GiB	3.33×
32,768	15.00 GiB	4.50 GiB	3.33×
65,536	30.00 GiB	9.00 GiB	3.33×
131,072	60.00 GiB	18.00 GiB	3.33×