[KongchangAI]
Unverified50% confidenceFactExact time

DeepSeek-V2-Lite is the lightweight MoE version of DeepSeek-V2, with about 16B total parameters and about 2.4B activated parameters, adopting MLA attention and a fine-grained expert design.

1
Sources
50%
Confidence
Long-term
Relevance
11/2/2026
First Seen

Sources

A New Perspective on Expert Pruning: Structural Redundancy and Preservation Framework for Large MoE Models

Related Entities

DeepSeek-V2-LitemodelDeepSeek-V2model

Related Claims

UnverifiedDeepSeek-Coder-V2-Lite is a programming-specific model that can run on 8 GB of VRAM after quantization.75% similarUnverifiedDeepSeek's Flash model has approximately 552 billion (552B) parameters, positioned as lightweight and efficient.74% similar

Cite This Claim

Stable URI
https://kongchang.com/claim/1125228
API
curl https://kongchang.com/api/v1/knowledge/claims/1125228
MCP
get_claim(id=1125228)