diff --git a/docs/SETUP.md b/docs/SETUP.md
index 5e3a8dc..8aa1d53 100644
--- a/docs/SETUP.md
+++ b/docs/SETUP.md
@@ -160,21 +160,5 @@ nvidia-device-plugin-daemonset-xjb5f                              1/1     Runnin
 nvidia-device-plugin-validator-dm69w                              0/1     Completed   0          14s
 nvidia-operator-validator-ztpls                                   1/1     Running     0          114s
 ```
-## Loading a local fmperf image into the cluster node
-
-Currently the fmperf load-tesing docker image is not available on a remote registry. Therefore,  we need to build a docker image from the Dockerfile provided in the repo, and load it into the cluster node.
-
-```
-docker build -t fmperf-project/fmperf:local .
-kind load fmperf-project/fmperf:local --name gpu-test
-```
-
-You can verify if this image is correctly loaded into the cluster node:
-
-```
-docker exec -it gpu-test-control-plane crictl images | grep local
-
-docker.io/fmperf-project/fmperf   local   c20f63b5bb19d    992M
-```
 
 The cluster is now ready to run the benchmark. As a first try, run the examples/example_vllm.py script.
diff --git a/examples/workload_specifications.yml b/examples/workload_specifications.yml
index 3761641..d943f3f 100644
--- a/examples/workload_specifications.yml
+++ b/examples/workload_specifications.yml
@@ -4,4 +4,4 @@ min_output_tokens: 50
 max_output_tokens: 50
 frac_greedy: 1.0
 sample_size: 1
-image: docker.io/fmperf-project/fmperf:local
+image: quay.io/fmperf/fmperf:main
diff --git a/fmperf/WorkloadSpecs.py b/fmperf/WorkloadSpecs.py
index d9a4000..0964442 100644
--- a/fmperf/WorkloadSpecs.py
+++ b/fmperf/WorkloadSpecs.py
@@ -5,7 +5,7 @@ class WorkloadSpec:
     def __init__(
         self,
         sample_size: int = 10,
-        image: str = "fmperf-project/fmperf:local",
+        image: str = "quay.io/fmperf/fmperf:main",
         pvc_name: str = None,
         overwrite: bool = False,
     ):
@@ -58,7 +58,7 @@ def __init__(
         max_output_tokens: int = 20,
         frac_greedy: float = 0.5,
         sample_size: int = 10,
-        image: str = "fmperf-project/fmperf:local",
+        image: str = "quay.io/fmperf/fmperf:main",
         pvc_name: str = None,
         overwrite: bool = False,
     ):
@@ -111,7 +111,7 @@ class HeterogeneousWorkloadSpec(WorkloadSpec):
     def __init__(
         self,
         sample_size: int = 10,
-        image: str = "fmperf-project/fmperf:local",
+        image: str = "quay.io/fmperf/fmperf:main",
         pvc_name: str = None,
         overwrite: bool = False,
     ):