Model comparison

DeepSeek-V4-Flash vs DeepSeek-V4-Flash-162B

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

DeepSeek-V4-FlashDeepSeek-V4-Flash-162B
Parameters291B92.2B
Architecturedeepseek4deepseek4
Layers4343
Native context1,048,5761,048,576
Mixture of expertsyes, 256 expertsyes, 144 experts
Quantizations published122
Smallest quantization76.87 GiB55.09 GiB
Q4_K_M
Licencemitmit

KV cache by context

the term that decides long-context viability
ContextDeepSeek-V4-FlashDeepSeek-V4-Flash-162BRatio
4,0960.06 GiB
8,1920.06 GiB
16,3840.06 GiB
32,7680.06 GiB
65,5360.06 GiB
131,0720.06 GiB
DeepSeek-V4-Flash vs DeepSeek-V4-Flash-162B — size, memory and hardware fit — ossmodeldb