Unverified50% confidenceFactExact time
The Engram n-gram memory module of DeepSeek-V4.1-Flash occupies 196 billion parameters.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/23/2026
First Seen
Valid until: 1/21/2027
Sources
Related Entities
Related Claims
UnverifiedQwen3.8 Flash Next additionally introduces an Ngram module with 51 billion parameters, resembling a massive local phrase memory table.74% similarUnverifiedv4.1 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.71% similarVerifiedDeepSeek-V4.1-Flash adopts a MoE (Mixture of Experts) backbone architecture with 552B parameters.71% similarUnverifiedBitRun v0.2 can run PrismML's 8-billion-parameter model bonsai-8b entirely in CPU memory, using about 2.08 GB of memory, without needing a discrete GPU, a cloud API, or compilation.68% similarVerifiedV4.1 Flash activates 8 billion parameters when processing input and activates 16 billion parameters when generating output.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088219API
curl https://kongchang.com/api/v1/knowledge/claims/1088219MCP
get_claim(id=1088219)