Compared　to　single-sensor　fault　diagnosis　models,　multi-sensor　information　fusion　models　utilize　potential　fault　information　from　various　sensors　for　more　precise　fault　diagnosis.　However,　most　fusion　models　require　many　training　samples　to　construct　accurate　models.　Collecting　these　data　is　costly　and　challenging,　increasing　the　time　needed　to　build　the　training　model.　These　models　typically　fuse　information　from　multiple　vibration　sensors,　with　limited　research　on　multi-modal　information　fusion,　such　as　combining　vibration　and　acoustic　data.　Additionally,　the　generality　of　existing　models　is　weak,　often　requiring　structural　and　parameter　adjustments　for　different　diagnostic　tasks.　To　address　these　challenges,　this　paper　proposes　a　high-accuracy　and　high-efficiency　mechanical　fault　diagnosis　model　based　on　the　multi-modal　multi-scale　multi-level　fusion　quadrant　entropy　(MMMFQE)　using　limited　training　samples.　The　proposed　MMMFQE　theory　effectively　constructs　multi-modal　information　fusion　feature　maps　across　multiple　scales　and　levels.　The　fusion　quadrant　entropy　is　then　proposed　to　accurately　characterize　the　mechanical　states　by　analyzing　the　complexities　of　fusion　feature　maps.　Analysis　of　two　industrial　datasets　shows　that　the　proposed　model　achieves　100%　and　99.46%　accuracy　with　only　five　training　samples　per　state.　Moreover,　the　accuracy,　efficiency,　and　few-shot　ability　of　the　proposed　model　surpass　those　of　several　advanced　models.