Is DeepSeek-V4-Flash or Qwen3-Coder-480B-A35B-Instruct smaller?

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

Which uses less memory at long context?

DeepSeek-V4-Flash — its KV cache at 32K context is 123.0x smaller, because of how its attention layers cache.

Model comparison

DeepSeek-V4-Flash vs Qwen3-Coder-480B-A35B-Instruct

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: DeepSeek-V4-Flash's KV cache at 32K is 123.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	DeepSeek-V4-Flash	Qwen3-Coder-480B-A35B-Instruct
Parameters	291B	480B
Architecture	deepseek4	qwen3moe
Layers	43	62
Native context	1,048,576	262,144
Mixture of experts	yes, 256 experts	yes, 160 experts
Quantizations published	12	41
Smallest quantization	76.87 GiB	123.78 GiB
Q4_K_M	—	270.14 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	DeepSeek-V4-Flash	Qwen3-Coder-480B-A35B-Instruct	Ratio
4,096	0.06 GiB	0.97 GiB	15.38×
8,192	0.06 GiB	1.94 GiB	30.76×
16,384	0.06 GiB	3.88 GiB	61.52×
32,768	0.06 GiB	7.75 GiB	123.04×
65,536	0.06 GiB	15.50 GiB	246.08×
131,072	0.06 GiB	31.00 GiB	492.16×