Is DeepSeek-V4-Flash or Infinity-Parser2-Pro 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 9.9x smaller, because of how its attention layers cache.

Model comparison

DeepSeek-V4-Flash vs Infinity-Parser2-Pro

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

From the file· summed bytes, KV per layer

Side by side

	DeepSeek-V4-Flash	Infinity-Parser2-Pro
Parameters	291B	35.1B
Architecture	deepseek4	qwen35moe
Layers	43	40
Native context	1,048,576	262,144
Mixture of experts	yes, 256 experts	yes, 256 experts
Quantizations published	12	1
Smallest quantization	76.87 GiB	34.37 GiB
Q4_K_M	—	—
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	DeepSeek-V4-Flash	Infinity-Parser2-Pro	Ratio
4,096	0.06 GiB	0.08 GiB	1.24×
8,192	0.06 GiB	0.16 GiB	2.48×
16,384	0.06 GiB	0.31 GiB	4.96×
32,768	0.06 GiB	0.63 GiB	9.92×
65,536	0.06 GiB	1.25 GiB	19.85×
131,072	0.06 GiB	2.50 GiB	39.69×