Is DeepSeek-V4-Flash or Qwen3-235B-A22B 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 93.3x smaller, because of how its attention layers cache.

Model comparison

DeepSeek-V4-Flash vs Qwen3-235B-A22B

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 93.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	DeepSeek-V4-Flash	Qwen3-235B-A22B
Parameters	291B	235B
Architecture	deepseek4	qwen3moe
Layers	43	94
Native context	1,048,576	40,960
Mixture of experts	yes, 256 experts	yes, 128 experts
Quantizations published	12	35
Smallest quantization	76.87 GiB	79.81 GiB
Q4_K_M	—	132.39 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	DeepSeek-V4-Flash	Qwen3-235B-A22B	Ratio
4,096	0.06 GiB	0.73 GiB	11.66×
8,192	0.06 GiB	1.47 GiB	23.32×
16,384	0.06 GiB	2.94 GiB	46.64×
32,768	0.06 GiB	5.88 GiB	93.27×
65,536	0.06 GiB	11.75 GiB	186.54×
131,072	0.06 GiB	23.50 GiB	373.09×