diff --git a/python/sglang/srt/model_loader/weight_utils.py b/python/sglang/srt/model_loader/weight_utils.py
index 6bc867c35..2afd8a8c2 100644
--- a/python/sglang/srt/model_loader/weight_utils.py
+++ b/python/sglang/srt/model_loader/weight_utils.py
@@ -1180,6 +1180,43 @@ def _drop_file_cache_after_load(path: str) -> None:
             os.close(fd)
 
 
+# [k3] Skip routed-expert tensors that this EP rank does not own BEFORE
+# reading them (mmap -> untouched bytes are never read). Enabled by
+# SGLANG_EXPERT_LOAD_FILTER=<num_routed_experts> (e.g. 896 for Kimi-K3).
+_B2_EXPERT_RE = None
+_B2_EXPERT_RANGE = None
+
+
+def _b2_skip_tensor(name: str) -> bool:
+    global _B2_EXPERT_RE, _B2_EXPERT_RANGE
+    n_exp = int(os.environ.get("SGLANG_EXPERT_LOAD_FILTER", "0") or 0)
+    if n_exp <= 0:
+        return False
+    if _B2_EXPERT_RANGE is None:
+        import re as _re
+
+        from sglang.srt.distributed import (
+            get_moe_expert_parallel_rank,
+            get_moe_expert_parallel_world_size,
+        )
+
+        _B2_EXPERT_RE = _re.compile(r"(?<!shared_)experts\.(\d+)\.")
+        ep = get_moe_expert_parallel_world_size()
+        r = get_moe_expert_parallel_rank()
+        per = n_exp // ep
+        _B2_EXPERT_RANGE = (r * per, (r + 1) * per)
+        logger.info(
+            "[k3] expert load filter: ep_rank %d/%d keeps experts [%d, %d)",
+            r, ep, *_B2_EXPERT_RANGE,
+        )
+    m = _B2_EXPERT_RE.search(name)
+    if m is None:
+        return False
+    e = int(m.group(1))
+    lo, hi = _B2_EXPERT_RANGE
+    return not (lo <= e < hi)
+
+
 def safetensors_weights_iterator(
     hf_weights_files: List[str],
     disable_mmap: bool = False,
@@ -1212,6 +1249,8 @@ def safetensors_weights_iterator(
         else:
             with safetensors.safe_open(st_file, framework="pt", device="cpu") as f:
                 for name in f.keys():
+                    if _b2_skip_tensor(name):
+                        continue
                     yield name, f.get_tensor(name)
         if drop_cache_after_load:
             _drop_file_cache_after_load(st_file)
@@ -1294,7 +1333,9 @@ def multi_thread_safetensors_weights_iterator(
                 result = safetensors.torch.load(f.read())
         else:
             with safetensors.safe_open(st_file, framework="pt", device="cpu") as f:
-                result = {k: f.get_tensor(k) for k in f.keys()}
+                result = {
+                    k: f.get_tensor(k) for k in f.keys() if not _b2_skip_tensor(k)
+                }
 
         return st_file, result
 
@@ -1349,7 +1390,9 @@ def buffered_multi_thread_safetensors_weights_iterator(
                 result = safetensors.torch.load(f.read())
         else:
             with safetensors.safe_open(st_file, framework="pt", device="cpu") as f:
-                result = {k: f.get_tensor(k) for k in f.keys()}
+                result = {
+                    k: f.get_tensor(k) for k in f.keys() if not _b2_skip_tensor(k)
+                }
         return result
 
     # Sliding window: max_workers loading + 1 prefetched.