Verified65% confidenceFactExact time
V4.1 Flash activates 8 billion parameters when processing input and activates 16 billion parameters when generating output.
3
Sources
65%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverifiedv4.1 Flash introduces a mechanism called Ngram, where 2 out of 40 layers contain conditional memory tables, with 196 billion parameters used for a lookup table that matches sequences of up to 4 tokens against a vocabulary of 16 million.75% similarVerifiedDeepSeek V4 Flash uses a Mixture of Experts (MOE) architecture with a total parameter count exceeding 600 billion (600B+).73% similarUnverifiedQwen3.8 Flash Next additionally introduces an Ngram module with 51 billion parameters, resembling a massive local phrase memory table.72% similarVerifiedPangu 2.0 Flash adopts a MoE (Mixture of Experts) architecture with a parameter scale of 92B A6B (92B total parameters, 6B activated parameters).70% similarUnverifiedv4.1 Flash's expert weights are shipped natively in FP4 (4 bits per parameter) and no 8-bit version has ever been released; being close to the compression limit of this format, it cannot be further quantized for Agentic tasks.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/909292API
curl https://kongchang.com/api/v1/knowledge/claims/909292MCP
get_claim(id=909292)