diff --git a/.gitmodules b/.gitmodules
index 6dc00a5..58b35de 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -3,4 +3,5 @@
 	url = https://github.com/microsoft/mimalloc.git
 [submodule "libmimalloc-sys/c_src/mimalloc3"]
 	path = libmimalloc-sys/c_src/mimalloc3
-	url = https://github.com/microsoft/mimalloc.git
+	url = https://github.com/napi-rs/mimalloc.git
+	branch = dev3
diff --git a/libmimalloc-sys/build.rs b/libmimalloc-sys/build.rs
index 3cfc819..6048cb3 100644
--- a/libmimalloc-sys/build.rs
+++ b/libmimalloc-sys/build.rs
@@ -76,34 +76,10 @@ fn main() {
         cmake_config.define("MI_LOCAL_DYNAMIC_TLS", "ON");
     }
 
-    // On Apple targets, mimalloc v3's `prim.h` selects
-    // `MI_TLS_MODEL_FIXED_SLOT` and hardcodes the per-thread `theap`
-    // pointer at TCB[108]/[109], reading/writing the slot directly
-    // through `tpidrro_el0` (arm64) or `%gs:` (x86_64) rather than
-    // through `pthread_setspecific`. The slot numbers are not allocated
-    // via `pthread_key_create`; the same header notes the caveat:
-    // "This goes wrong though if the OS or a library uses the same
-    // fixed slot."
-    //
-    // When a process loads more than one image that statically links
-    // mimalloc-safe (e.g. two napi addons in one Node.js process),
-    // each image has its own mimalloc state but every image's
-    // `_mi_theap_default()` reads and writes the same TCB[108] on any
-    // given thread — the instances overwrite each other's pointers.
-    //
-    // `-DMI_HAS_TLS_SLOT=0` makes the cascade in `prim.h` skip the
-    // FIXED_SLOT branch on Apple and fall through to
-    // `MI_TLS_MODEL_DYNAMIC_PTHREADS`, whose accessors use
-    // `pthread_{get,set}specific` with a key allocated per image via
-    // `pthread_key_create`. Different images then use distinct keys and
-    // no longer share TLS storage. `prim.h` notes this path is "a bit
-    // slower"; the impact has not been measured here.
-    //
-    // Gated on the `v3` feature: v2 has a separate Apple fast path
-    // controlled by `MI_TLS_SLOT` and is not affected by this define.
-    if target_os == "macos" && env::var_os("CARGO_FEATURE_V3").is_some() {
-        cmake_config.cflag("-DMI_HAS_TLS_SLOT=0");
-    }
+    // Note: the previous `-DMI_HAS_TLS_SLOT=0` workaround for Apple has been
+    // replaced by a vendored source patch in our mimalloc fork (napi-rs/mimalloc
+    // dev3) that routes Apple to `MI_TLS_MODEL_THREAD_LOCAL + MI_TLS_RECURSE_GUARD`
+    // directly in `include/mimalloc/prim.h`. See that patch for the full rationale.
 
     if (target_os == "linux" || target_os == "android")
         && env::var_os("CARGO_FEATURE_NO_THP").is_some()
diff --git a/libmimalloc-sys/c_src/mimalloc3 b/libmimalloc-sys/c_src/mimalloc3
index 30b2d9d..9a15529 160000
--- a/libmimalloc-sys/c_src/mimalloc3
+++ b/libmimalloc-sys/c_src/mimalloc3
@@ -1 +1 @@
-Subproject commit 30b2d9d89099bee08e9f67a1ffb3e12e7ba45227
+Subproject commit 9a15529dc99d27fb7983eed37b4290b541834c86