diff --git a/src/openfe/protocols/openmm_utils/omm_compute.py b/src/openfe/protocols/openmm_utils/omm_compute.py
index 1779af2bf..a09420040 100644
--- a/src/openfe/protocols/openmm_utils/omm_compute.py
+++ b/src/openfe/protocols/openmm_utils/omm_compute.py
@@ -52,6 +52,7 @@ def get_openmm_platform(
                 "cpu": "CPU",
                 "opencl": "OpenCL",
                 "cuda": "CUDA",
+                "hip": "HIP",
             }[str(platform_name).lower()]
         except KeyError:
             pass
@@ -61,18 +62,18 @@ def get_openmm_platform(
         platform = Platform.getPlatformByName(platform_name)
     # Set precision and properties
     name = platform.getName()
-    if name in ["CUDA", "OpenCL"]:
+    if name in ["CUDA", "OpenCL", "HIP"]:
         platform.setPropertyDefaultValue("Precision", "mixed")
         if gpu_device_index is not None:
             index_list = ",".join(str(i) for i in gpu_device_index)
             platform.setPropertyDefaultValue("DeviceIndex", index_list)
 
-    if name == "CUDA":
+    if name in ["CUDA", "HIP"]:
         platform.setPropertyDefaultValue("DeterministicForces", "true")
 
-    if name != "CUDA":
+    if name not in ["CUDA", "HIP"]:
         wmsg = (
-            f"Non-CUDA platform selected: {name}, this may significantly "
+            f"Either a non GPU platform or OpenCL selected: {name}, this may significantly "
             "impact simulation performance"
         )
         warnings.warn(wmsg)
diff --git a/src/openfe/protocols/openmm_utils/omm_settings.py b/src/openfe/protocols/openmm_utils/omm_settings.py
index 97c7ad8ce..1fce1a612 100644
--- a/src/openfe/protocols/openmm_utils/omm_settings.py
+++ b/src/openfe/protocols/openmm_utils/omm_settings.py
@@ -329,9 +329,12 @@ class OpenMMEngineSettings(SettingsBaseModel):
     """
     OpenMM compute platform to perform MD integration with. If ``None``, will
     choose fastest available platform.
-    Allowed platforms are; ``cuda``, ``opencl``, ``cpu``.
+    Allowed platforms are; ``cuda``, ``opencl``, ``cpu``, and ``hip``.
     Default ``cuda``.
 
+    Notes
+    -----
+    To use the ``hip`` platform, you will need to install ``openmm-hip``.
     """
     gpu_device_index: Optional[list[int]] = None
     """
@@ -348,7 +351,7 @@ class OpenMMEngineSettings(SettingsBaseModel):
 
     @field_validator("compute_platform")
     def supported_sampler(cls, v):
-        supported = ["cpu", "opencl", "cuda"]
+        supported = ["cpu", "opencl", "cuda", "hip"]
         if v is not None and v.lower() not in supported:
             errmsg = f"Only the following OpenMM compute backends are supported: {supported}"
             raise ValueError(errmsg)