diff --git a/cuda_bindings/tests/test_cuda.py b/cuda_bindings/tests/test_cuda.py
index d85724fe49a..8282f21673b 100644
--- a/cuda_bindings/tests/test_cuda.py
+++ b/cuda_bindings/tests/test_cuda.py
@@ -17,6 +17,11 @@
 from cuda.bindings._internal.utils import FunctionNotFoundError
 from cuda_python_test_helpers import driver_version_less_than
 
+# Cap for memory pools created by tests. A pool created with maxSize 0 reserves
+# virtual address space of about twice the device memory, and that reservation
+# can fail on systems with a limited virtual address space.
+POOL_SIZE = 2 * 1024 * 1024  # 2 MiB
+
 
 def supportsMemoryPool():
     err, isSupported = cudart.cudaDeviceGetAttribute(cudart.cudaDeviceAttr.cudaDevAttrMemoryPoolsSupported, 0)
@@ -265,6 +270,7 @@ def test_cuda_memPool_attr():
     poolProps.allocType = cuda.CUmemAllocationType.CU_MEM_ALLOCATION_TYPE_PINNED
     poolProps.location.id = 0
     poolProps.location.type = cuda.CUmemLocationType.CU_MEM_LOCATION_TYPE_DEVICE
+    poolProps.maxSize = POOL_SIZE
 
     attr_list = [None] * 8
     err, pool = cuda.cuMemPoolCreate(poolProps)
@@ -460,11 +466,29 @@ def test_cuda_mem_range_attr(device):
     assert err == cuda.CUresult.CUDA_SUCCESS
 
 
+@pytest.fixture
+def xfail_on_graph_mempool_oom():
+    """Return a check that xfails the calling test if the graph memory pool cannot be created.
+
+    The graph memory pool reserves virtual address space of about twice the
+    device memory, and unlike pools from cuMemPoolCreate it cannot be capped.
+    On systems with a limited virtual address space this reservation can fail
+    with CUDA_ERROR_OUT_OF_MEMORY, especially when another uncapped pool
+    already exists in the process.
+    """
+
+    def check(err):
+        if err == cuda.CUresult.CUDA_ERROR_OUT_OF_MEMORY:
+            pytest.xfail("graph memory pool creation failed with CUDA_ERROR_OUT_OF_MEMORY")
+
+    return check
+
+
 @pytest.mark.skipif(
     driver_version_less_than(11040) or not supportsMemoryPool(), reason="Mempool for graphs not supported"
 )
 @pytest.mark.thread_unsafe(reason="used high memory can be higher if threaded.")
-def test_cuda_graphMem_attr(device):
+def test_cuda_graphMem_attr(device, xfail_on_graph_mempool_oom):
     err, stream = cuda.cuStreamCreate(0)
     assert err == cuda.CUresult.CUDA_SUCCESS
 
@@ -485,6 +509,7 @@ def test_cuda_graphMem_attr(device):
         assert destroy_err == cuda.CUresult.CUDA_SUCCESS
         (destroy_err,) = cuda.cuStreamDestroy(stream)
         assert destroy_err == cuda.CUresult.CUDA_SUCCESS
+        xfail_on_graph_mempool_oom(err)
     assert err == cuda.CUresult.CUDA_SUCCESS
     err, freeNode = cuda.cuGraphAddMemFreeNode(graph, [allocNode], 1, params.dptr)
     assert err == cuda.CUresult.CUDA_SUCCESS
diff --git a/cuda_bindings/tests/test_cudart.py b/cuda_bindings/tests/test_cudart.py
index b16391210ed..f1c263f7c13 100644
--- a/cuda_bindings/tests/test_cudart.py
+++ b/cuda_bindings/tests/test_cudart.py
@@ -13,6 +13,11 @@
 from cuda.bindings import runtime
 from cuda_python_test_helpers import driver_version_less_than
 
+# Cap for memory pools created by tests. A pool created with maxSize 0 reserves
+# virtual address space of about twice the device memory, and that reservation
+# can fail on systems with a limited virtual address space.
+POOL_SIZE = 2 * 1024 * 1024  # 2 MiB
+
 
 def isSuccess(err):
     return err == cudart.cudaError_t.cudaSuccess
@@ -520,6 +525,7 @@ def test_cudart_MemPool_attr():
     poolProps.allocType = cudart.cudaMemAllocationType.cudaMemAllocationTypePinned
     poolProps.location.id = 0
     poolProps.location.type = cudart.cudaMemLocationType.cudaMemLocationTypeDevice
+    poolProps.maxSize = POOL_SIZE
 
     attr_list = [None] * 8
     err, pool = cudart.cudaMemPoolCreate(poolProps)