Is Infinity-Parser2-Pro or DeepSeek-V4-Flash 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

Infinity-Parser2-Pro vs DeepSeek-V4-Flash

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

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

KV cache by context

the term that decides long-context viability

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