Unverified60% confidenceFactExact time
DeepSeek V3's activated parameters are compressed to 3 to 5 billion, with a total parameter count of 671B.
2
Sources
60%
Confidence
Long-term
Relevance
7/22/2026
First Seen
Sources
Related Claims
UnverifiedIn the DeepSeek V1 era, each incremental token required nearly 400 KB of KV cache, which dropped to 48 KB in V3.2.78% similarUnverifiedDeepSeek-V3 has a total of 685B parameters, and even after Q4 quantization its size still exceeds 400GB.76% similarUnverifiedThe DeepSeek distilled versions range in parameter count from 1.5B to 70B.76% similarUnverifiedDeepSeek V4 Pro 0423's channel input price is 40% lower than the official input price, and its output price is 51% lower.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/587697API
curl https://kongchang.com/api/v1/knowledge/claims/587697MCP
get_claim(id=587697)