diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 74c99390fa4d..2e18d62df346 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -54,8 +54,11 @@ jobs:
             container_image: alpine:3.21
             host_dmd: ldmd2
           # macOS
-          - job_name: macOS 13 x64, DMD (latest)
-            os: macos-13
+          - job_name: macOS 14 arm64, LDC
+            os: macos-14
+            host_dmd: ldc
+          - job_name: macOS 14 x64, DMD (latest)
+            os: macos-14
             host_dmd: dmd
           # Disabled because of failure https://issues.dlang.org/show_bug.cgi?id=24518
           # - job_name: macOS 13 x64, DMD (coverage)
@@ -79,7 +82,8 @@ jobs:
     name: ${{ matrix.job_name }}
     runs-on: ${{ matrix.os }}
     container: ${{ matrix.container_image }}
-    timeout-minutes: 40
+    # for some reason, the compiler testsuite is extremely slow with x86_64 emulation on macos-14 runners
+    timeout-minutes: ${{ matrix.os == 'macos-14' && 60 || 40 }}
     env:
       # for ci/run.sh:
       OS_NAME: ${{ startsWith(matrix.os, 'ubuntu') && 'linux' || (startsWith(matrix.os, 'macos') && 'osx' || (startsWith(matrix.os, 'windows') && 'windows' || '')) }}
@@ -156,7 +160,20 @@ jobs:
         uses: seanmiddleditch/gha-setup-vsdevenv@v4
         with:
           arch: ${{ env.MODEL == '64' && 'x64' || 'x86' }}
+      - name: 'macOS arm64: Run arm64 smoke test'
+        if: matrix.os == 'macos-14'
+        run: |
+          set -uexo pipefail
+
+          cat >hello.d <<EOF
+          version (AArch64) {} else static assert(0);
+          extern(C) int puts(const(char)* s);
+          extern(C) int main() { puts("Hello world from native arm64!"); return 0; }
+          EOF
+
+          generated/osx/release/64/dmd -betterC -arm -run hello.d
       - name: Test dmd
+        if: success() || failure()
         run: ci/run.sh test_dmd
       - name: Test druntime
         if: '!matrix.coverage && (success() || failure())'
diff --git a/ci/cirrusci.sh b/ci/cirrusci.sh
index 776c6a2e7a5d..85ab45d6bf03 100755
--- a/ci/cirrusci.sh
+++ b/ci/cirrusci.sh
@@ -36,7 +36,12 @@ if [ "$OS_NAME" == "linux" ]; then
 elif [ "$OS_NAME" == "osx" ]; then
   # upgrade GNU make
   brew install make
-  sudo ln -s /usr/local/opt/make/libexec/gnubin/make /usr/local/bin/make
+  for candidateDir in /usr/local/opt/make/libexec/gnubin /opt/homebrew/opt/make/libexec/gnubin; do
+    if [[ -f $candidateDir/make ]]; then
+      sudo ln -s $candidateDir/make /usr/local/bin/make
+      break
+    fi
+  done
 elif [ "$OS_NAME" == "freebsd" ]; then
   packages="git gmake devel/llvm12"
   if [ "$HOST_DMD" == "dmd-2.079.0" ] ; then
diff --git a/compiler/src/dmd/backend/mach.d b/compiler/src/dmd/backend/mach.d
index a7078e2766f7..3bcd8927bea8 100644
--- a/compiler/src/dmd/backend/mach.d
+++ b/compiler/src/dmd/backend/mach.d
@@ -25,10 +25,13 @@ enum
     CPU_TYPE_X86_64    = cast(cpu_type_t)7 | 0x1000000,
     CPU_TYPE_POWERPC   = cast(cpu_type_t)18,
     CPU_TYPE_POWERPC64 = CPU_TYPE_POWERPC | 0x1000000,
+    CPU_TYPE_ARM       = cast(cpu_type_t)12,
+    CPU_TYPE_ARM64     = CPU_TYPE_ARM | 0x1000000,
 
     // cpusubtype
     CPU_SUBTYPE_POWERPC_ALL = cast(cpu_subtype_t)0,
     CPU_SUBTYPE_I386_ALL    = cast(cpu_subtype_t)3,
+    CPU_SUBTYPE_ARM64_ALL   = cast(cpu_subtype_t)0,
 
     // filetype
     MH_OBJECT       = 1,
diff --git a/compiler/src/dmd/backend/machobj.d b/compiler/src/dmd/backend/machobj.d
index dc89956beb5d..c4adae38138b 100644
--- a/compiler/src/dmd/backend/machobj.d
+++ b/compiler/src/dmd/backend/machobj.d
@@ -642,9 +642,10 @@ void MachObj_term(const(char)[] objfilename)
     {
         mach_header_64 header = void;
 
+        const isARM64 = config.target_cpu == TARGET_AArch64;
         header.magic = MH_MAGIC_64;
-        header.cputype = CPU_TYPE_X86_64;
-        header.cpusubtype = CPU_SUBTYPE_I386_ALL;
+        header.cputype = isARM64 ? CPU_TYPE_ARM64 : CPU_TYPE_X86_64;
+        header.cpusubtype = isARM64 ? CPU_SUBTYPE_ARM64_ALL : CPU_SUBTYPE_I386_ALL;
         header.filetype = MH_OBJECT;
         header.ncmds = 4;
         header.sizeofcmds = cast(uint)(segment_command_64.sizeof +
diff --git a/compiler/src/dmd/backend/x86/cg87.d b/compiler/src/dmd/backend/x86/cg87.d
index d1cd09a00af9..4971bd69b09f 100644
--- a/compiler/src/dmd/backend/x86/cg87.d
+++ b/compiler/src/dmd/backend/x86/cg87.d
@@ -649,7 +649,7 @@ ubyte loadconst(elem* e, int im)
     immutable double[7] dval =
         [0.0,1.0,PI,LOG2T,LOG2E,LOG2,LN2];
 
-    static if (real.sizeof < 10)
+    static if (!is(targ_ldouble == real))
     {
         import dmd.root.longdouble;
         immutable targ_ldouble[7] ldval =
@@ -742,7 +742,7 @@ ubyte loadconst(elem* e, int im)
     // Note that for this purpose, -0 is not regarded as +0,
     // since FLDZ loads a +0
     assert(sz <= zeros.length);
-    zero = (memcmp(p, zeros.ptr, sz) == 0);
+    zero = (memcmp(p, zeros.ptr, sz < targ_ldouble.sizeof ? sz : targ_ldouble.sizeof) == 0);
     if (zero && config.target_cpu >= TARGET_PentiumPro)
         return 0xEE;            // FLDZ is the only one with 1 micro-op
 
diff --git a/compiler/src/dmd/lib/scanmach.d b/compiler/src/dmd/lib/scanmach.d
index 0d0d5c28716f..ee0a7019cc3f 100644
--- a/compiler/src/dmd/lib/scanmach.d
+++ b/compiler/src/dmd/lib/scanmach.d
@@ -19,6 +19,7 @@ import dmd.location;
 //import core.sys.darwin.mach.loader;
 import dmd.backend.mach;
 import dmd.root.string : fTuple;
+import dmd.target : target;
 
 nothrow:
 
@@ -79,9 +80,10 @@ void scanMachObjModule(void delegate(const(char)[] name, int pickAny) nothrow pA
         header64 = cast(mach_header_64*)buf;
         if (buflen < mach_header_64.sizeof)
             return corrupt(__LINE__);
-        if (header64.cputype != CPU_TYPE_X86_64)
+        const expectedCPUType = target.isAArch64 ? CPU_TYPE_ARM64 : CPU_TYPE_X86_64;
+        if (header64.cputype != expectedCPUType)
         {
-            eSink.error(Loc.initial, "Mach-O object module `%s` has cputype = %d, should be %d", module_name, header64.cputype, CPU_TYPE_X86_64);
+            eSink.error(Loc.initial, "Mach-O object module `%s` has cputype = %d, should be %d", module_name, header64.cputype, expectedCPUType);
             return;
         }
         if (header64.filetype != MH_OBJECT)
diff --git a/compiler/src/dmd/link.d b/compiler/src/dmd/link.d
index a0850b829165..2402ed6682ab 100644
--- a/compiler/src/dmd/link.d
+++ b/compiler/src/dmd/link.d
@@ -443,10 +443,31 @@ public int runLINK(bool verbose, ErrorSink eSink)
             argv.push("-g");
         if (target.isX86_64)
             argv.push("-m64");
-        else
+        else if (target.isX86)
             argv.push("-m32");
         version (OSX)
         {
+            // might need to set up Apple clang for cross-linking
+            if (target.os == Target.OS.OSX)
+            {
+                version (AArch64)
+                {
+                    if (target.isX86_64)
+                    {
+                        argv.push("-arch");
+                        argv.push("x86_64");
+                    }
+                }
+                else
+                {
+                    if (target.isAArch64)
+                    {
+                        argv.push("-arch");
+                        argv.push("arm64");
+                    }
+                }
+            }
+
             /* Without this switch, ld generates messages of the form:
              * ld: warning: could not create compact unwind for __Dmain: offset of saved registers too far to encode
              * meaning they are further than 255 bytes from the frame register.
diff --git a/compiler/src/dmd/target.d b/compiler/src/dmd/target.d
index f52bcc57b8f2..61e4a44f9c0b 100644
--- a/compiler/src/dmd/target.d
+++ b/compiler/src/dmd/target.d
@@ -485,6 +485,22 @@ extern (C++) struct Target
             }
         }
 
+        // fix up RealProperties if the target real is x87, but host real_t isn't
+        if (realsize - realpad == 10 && RealProperties.mant_dig != 64) {
+            import dmd.root.ctfloat : CTFloat;
+
+            bool isOutOfRange;
+            RealProperties.max = CTFloat.parse("0x1.fffffffffffffffep+16383", isOutOfRange);
+            RealProperties.min_normal = CTFloat.parse("0x1p-16382", isOutOfRange);
+            RealProperties.epsilon = CTFloat.parse("0x1p-63", isOutOfRange);
+            RealProperties.dig = 18;
+            RealProperties.mant_dig = 64;
+            RealProperties.max_exp = 16_384;
+            RealProperties.min_exp = -16_381;
+            RealProperties.max_10_exp = 4932;
+            RealProperties.min_10_exp = -4931;
+        }
+
         c.initialize(params, this);
         cpp.initialize(params, this);
         objc.initialize(params, this);