Azure SQL Managed Instance PREDICT with an ONNX model

I repeat the example from https://docs.microsoft.com/en-us/azure/azure-sql-edge/deploy-onnx "Deploy and make predictions with an ONNX model and SQL machine learning" In this quickstart, you'll learn how to train a model, convert it to ONNX, deploy it to Azure SQL Edge, and then run native PREDICT on data using the uploaded ONNX model.

Successfully create a model using Python, convert to onnx format, I test the model using Python, save the model to the database, load the necessary data and try to execute the SQL query

USE onnx
DECLARE @model VARBINARY(max) = (
    SELECT DATA
    FROM dbo.models
    WHERE id = 1
    );
WITH predict_input
AS (
    SELECT TOP (1000) [id]
    , CRIM
    , ZN
    , INDUS
    , CHAS
    , NOX
    , RM
    , AGE
    , DIS
    , RAD
    , TAX
    , PTRATIO
    , B
    , LSTAT
FROM [dbo].[features]
)
SELECT predict_input.id
, p.variable1 AS MEDV
FROM PREDICT(MODEL = @model, DATA = predict_input, RUNTIME=ONNX) WITH (variable1 FLOAT) AS p;

As a result I get an error Msg 102, Level 16, State 5, Line 27 Incorrect syntax near 'RUNTIME'.

I can't figure out what's wrong. The documentation clearly says "The RUNTIME = ONNX argument is only available in Azure SQL Edge, Azure Synapse Analytics, and is in Preview in Azure SQL Managed Instance."