Is DeepSeek-V4-Flash or Qwen3.5-REAP-212B-A17B 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 14.9x smaller, because of how its attention layers cache.

Model comparison

DeepSeek-V4-Flash vs Qwen3.5-REAP-212B-A17B

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

From the file· summed bytes, KV per layer

Side by side

	DeepSeek-V4-Flash	Qwen3.5-REAP-212B-A17B
Parameters	291B	212B
Architecture	deepseek4	qwen35moe
Layers	43	60
Native context	1,048,576	262,144
Mixture of experts	yes, 256 experts	yes, 267 experts
Quantizations published	12	8
Smallest quantization	76.87 GiB	52.41 GiB
Q4_K_M	—	119.56 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	DeepSeek-V4-Flash	Qwen3.5-REAP-212B-A17B	Ratio
4,096	0.06 GiB	0.12 GiB	1.86×
8,192	0.06 GiB	0.23 GiB	3.72×
16,384	0.06 GiB	0.47 GiB	7.44×
32,768	0.06 GiB	0.94 GiB	14.89×
65,536	0.06 GiB	1.88 GiB	29.77×
131,072	0.06 GiB	3.75 GiB	59.54×