Unified　stream　and　batch　computing　(USBC)　aims　to　incorporate　stream　and　batch　computation　into　a　unified　framework,　thereby　enabling　the　development　of　a　one-stop　solution　for　stream　and　batch　data　processing　and　enhancing　the　generalization　of　the　framework.　However,　research　on　unified　graph　computing　models　(UGCMs)　faces　several　challenges.　First,　existing　UGCMs　need　to　consider　all　graph　information　in　the　cache　during　the　incremental　update　phase,　thus　leading　to　decreased　execution　efficiency.　Second,　existing　UGCMs　use　fixed　bytes　to　store　nodes　without　considering　the　actual　space　occupied　by　nodes　resulting　in　wasted　memory　when　dealing　with　large　graphs.　This　paper　proposes　a　UGCM　with　Local　Updates　for　community　detection　(UGCM-LU).　We　first　implement　a　local　update　strategy　to　consider　partial　information　of　the　graph　to　achieve　incremental　updates.　Secondly,　we　also　designed　a　byte-compression-based　module　to　store　graph　data　according　to　the　space　occupied　by　nodes.　The　experimental　results　show　the　effectiveness　and　efficiency　of　the　model　in　real-world　and　artificial　networks.　©　The　Author(s),　under　exclusive　license　to　Springer　Nature　Singapore　Pte　Ltd.　2025.