diff --git a/benchmark/README.md b/benchmark/README.md
index aa5ef10a..a92013f9 100644
--- a/benchmark/README.md
+++ b/benchmark/README.md
@@ -5,7 +5,7 @@ Tart comes with a Golang-based benchmarking utility that allows one to easily co
 Currently, only Flexible I/O tester workloads are supported. To run them, [install Golang](https://go.dev/) and run the following command from this (`benchmark/`) directory:
 
 ```shell
-go run cmd/main.go fio
+go run cmd/main.go fio --image ghcr.io/cirruslabs/macos-sonoma-base:latest
 ```
 
 You can also enable the debugging output to diagnose issues:
diff --git a/benchmark/internal/command/fio/fio.go b/benchmark/internal/command/fio/fio.go
index 98a8ae78..aae969f2 100644
--- a/benchmark/internal/command/fio/fio.go
+++ b/benchmark/internal/command/fio/fio.go
@@ -15,6 +15,7 @@ import (
 )
 
 var debug bool
+var image string
 
 func NewCommand() *cobra.Command {
 	cmd := &cobra.Command{
@@ -24,6 +25,7 @@ func NewCommand() *cobra.Command {
 	}
 
 	cmd.Flags().BoolVar(&debug, "debug", false, "enable debug logging")
+	cmd.Flags().StringVar(&image, "image", "ghcr.io/cirruslabs/macos-sonoma-base:latest", "image to use for testing")
 
 	return cmd
 }
@@ -111,7 +113,7 @@ func initializeExecutors(ctx context.Context, logger *zap.Logger) ([]executor.Ex
 
 	logger.Info("initializing Tart executor")
 
-	tart, err := tart.New(ctx, logger)
+	tart, err := tart.New(ctx, image, logger)
 	if err != nil {
 		return nil, err
 	}
diff --git a/benchmark/internal/executor/tart/tart.go b/benchmark/internal/executor/tart/tart.go
index 4ebb0fc0..de35d55b 100644
--- a/benchmark/internal/executor/tart/tart.go
+++ b/benchmark/internal/executor/tart/tart.go
@@ -14,8 +14,6 @@ import (
 	"time"
 )
 
-const baseImage = "ghcr.io/cirruslabs/macos-sonoma-base:latest"
-
 type Tart struct {
 	vmRunCancel context.CancelFunc
 	vmName      string
@@ -23,17 +21,17 @@ type Tart struct {
 	logger      *zap.Logger
 }
 
-func New(ctx context.Context, logger *zap.Logger) (*Tart, error) {
+func New(ctx context.Context, image string, logger *zap.Logger) (*Tart, error) {
 	tart := &Tart{
 		vmName: fmt.Sprintf("tart-benchmark-%s", uuid.NewString()),
 		logger: logger,
 	}
 
-	if err := Cmd(ctx, tart.logger, "pull", baseImage); err != nil {
+	if err := Cmd(ctx, tart.logger, "pull", image); err != nil {
 		return nil, err
 	}
 
-	if err := Cmd(ctx, tart.logger, "clone", baseImage, tart.vmName); err != nil {
+	if err := Cmd(ctx, tart.logger, "clone", image, tart.vmName); err != nil {
 		return nil, err
 	}
 
diff --git a/benchmark/internal/executor/tart/tart_test.go b/benchmark/internal/executor/tart/tart_test.go
index 46b2136a..d11c4ab8 100644
--- a/benchmark/internal/executor/tart/tart_test.go
+++ b/benchmark/internal/executor/tart/tart_test.go
@@ -11,7 +11,7 @@ import (
 func TestTart(t *testing.T) {
 	ctx := context.Background()
 
-	tart, err := tart.New(ctx, zap.NewNop())
+	tart, err := tart.New(ctx, "ghcr.io/cirruslabs/macos-sonoma-base:latest", zap.NewNop())
 	require.NoError(t, err)
 
 	output, err := tart.Run(ctx, "echo \"this is a test\"")