Is DeepSeek-V4-Flash or gpt-oss-120b-uncensored-bf16 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 18.3x smaller, because of how its attention layers cache.

Model comparison

DeepSeek-V4-Flash vs gpt-oss-120b-uncensored-bf16

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

From the file· summed bytes, KV per layer

Side by side

	DeepSeek-V4-Flash	gpt-oss-120b-uncensored-bf16
Parameters	291B	117B
Architecture	deepseek4	gpt-oss
Layers	43	36
Native context	1,048,576	131,072
Mixture of experts	yes, 256 experts	yes, 128 experts
Quantizations published	12	18
Smallest quantization	76.87 GiB	58.30 GiB
Q4_K_M	—	58.53 GiB
Licence	mit	—

KV cache by context

the term that decides long-context viability

Context	DeepSeek-V4-Flash	gpt-oss-120b-uncensored-bf16	Ratio
4,096	0.06 GiB	0.17 GiB	2.65×
8,192	0.06 GiB	0.31 GiB	4.88×
16,384	0.06 GiB	0.59 GiB	9.35×
32,768	0.06 GiB	1.15 GiB	18.28×
65,536	0.06 GiB	2.28 GiB	36.14×
131,072	0.06 GiB	4.53 GiB	71.86×