Is DeepSeek-V4-Flash or Solar-Open2-250B 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 95.3x smaller, because of how its attention layers cache.

Model comparison

DeepSeek-V4-Flash vs Solar-Open2-250B

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

From the file· summed bytes, KV per layer

Side by side

	DeepSeek-V4-Flash	Solar-Open2-250B
Parameters	291B	250B
Architecture	deepseek4	solar-open2
Layers	43	48
Native context	1,048,576	1,048,576
Mixture of experts	yes, 256 experts	yes, 320 experts
Quantizations published	12	13
Smallest quantization	76.87 GiB	52.67 GiB
Q4_K_M	—	141.39 GiB
Licence	mit	other

KV cache by context

the term that decides long-context viability

Context	DeepSeek-V4-Flash	Solar-Open2-250B	Ratio
4,096	0.06 GiB	0.75 GiB	11.91×
8,192	0.06 GiB	1.50 GiB	23.81×
16,384	0.06 GiB	3.00 GiB	47.63×
32,768	0.06 GiB	6.00 GiB	95.26×
65,536	0.06 GiB	12.00 GiB	190.51×
131,072	0.06 GiB	24.00 GiB	381.02×