Expired65% confidenceFactTime unknown
DeepSeek-V4 Pro has 1.6T parameters with 49B activated per inference; the Flash version has 284B parameters with 13B activated.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
6/3/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/1/2026(expired)
Sources
Related Entities
Related Claims
VerifiedDeepSeek V4 Flash has 284B total parameters, activates 13B per inference, and requires approximately 150GB of VRAM.82% similarUnverifiedV4-Flash has a total parameter count of 284B and only 13B active parameters.76% similarUnverifiedDeepSeek V3's activated parameters are compressed to 3 to 5 billion, with a total parameter count of 671B.76% similarUnverifiedDeepSeek V4's maximum output can reach 384K tokens, while GPT-5.5's is 128K tokens.73% similarUnverifiedDeepSeek V4 Flash's KV Cache VRAM has been reduced to 7% of the V3.2 version (a 13.7x reduction).72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/39254API
curl https://kongchang.com/api/v1/knowledge/claims/39254MCP
get_claim(id=39254)