All Products
Search
Document Center

MaxCompute:MaxCompute models

Last Updated:Jun 29, 2026

A model is one of the core objects in MaxCompute. MaxCompute supports various model types, including public, imported, and remote models. It provides unified management for models and model versions, helping you seamlessly integrate AI capabilities into your business analysis workflows. This topic describes the concepts, benefits, and types of MaxCompute models, and explains how to manage and use them.

Model overview

Key concepts

  • model: A deployment object registered in MaxCompute for prediction or generation tasks. It seamlessly integrates AI capabilities, such as large language models (LLMs) and machine learning models, into the platform where your data resides.

  • model version: An independent and uniquely identifiable sub-object of a model. You can create and manage multiple iterative versions under the same model name. This simplifies gradual rollouts, rapid rollbacks, and side-by-side performance comparisons when you call models by using an AI Function.

Benefits

  • Unified management: MaxCompute provides multiple model types, which, like data, support permission control and versioning to meet enterprise security and compliance requirements.

  • Multi-engine support: You can call models from various ecosystems, such as SQL and Python (MaxFrame). This unified architecture not only allows data analysts to use familiar SQL to call powerful AI models but also enables data scientists to use the distributed Python computing power of MaxFrame to improve data preprocessing efficiency and quality.

  • Simplified O&M: You can perform AI inference without exporting data. This eliminates the security risks, costs, and latency of data movement.

Model types

MaxCompute provides the following types of models:

Model type

Description

Tutorial

Public model

  • MaxCompute offers built-in, open-source large models pre-created in a public project named BIGDATA_PUBLIC_MODELSET and its public schema named default.

  • No creation or management is required; simply call the models using an AI Function. This approach lowers the barrier to entry.

  • When you use a public model:

    • If tenant-level schema syntax is disabled for the project, use bigdata_public_modelset.<model_name>.

    • If tenant-level schema syntax is enabled for the project, you must specify bigdata_public_modelset.default.<model_name>.

Use a MaxCompute public model for sentiment analysis of online reviews

Remote model

Connect to models deployed on PAI-EAS. Register them as MaxCompute remote models by providing the PAI-EAS endpoint and access token. You can then call the models using an AI Function.

Use a MaxCompute remote model to automatically generate e-commerce product selection descriptions

Internally trained model

You can use MaxCompute MaxFrame to train traditional machine learning models. Then, run TO_ODPS_MODEL to save the model as an internally trained model in MaxCompute.

Use MaxCompute for XGBoost model training and prediction

Imported model

When built-in public models are insufficient, you can import externally fine-tuned models for better performance tailored to your business needs.

Import custom, externally trained models by specifying their OSS path. MaxCompute can then use them for inference.

Being rolled out

Use the MaxCompute AI Function to call built-in public models or other models you have created.

Public models and applicable quotas

Public model name

Applicable quota

  • qwen3.7-max

  • qwen3.7-plus

  • qwen3-vl-embedding

  • text-embedding-v4

  • qwen3.6-plus

  • qwen3.6-flash

  • deepseek-v4-pro

  • deepseek-v4-flash

  • qwen3.5-397b-a17b

  • qwen3-asr-flash

  • qwen3-max (to be deprecated)

  • Pay-as-you-go model computing service (token-based)

  • Qwen3-0.6B-GGUF

  • Qwen3-1.7B-GGUF

  • Qwen3-4B-GGUF

  • Qwen3-8B-GGUF

  • Qwen3-14B-GGUF

  • DeepSeek-R1-Distill-Qwen-1.5B

  • DeepSeek-R1-Distill-Qwen-7B

  • DeepSeek-R1-Distill-Qwen-14B

  • DeepSeek-R1-0528-Qwen3-8B

  • Pay-as-you-go standard computing resources (CU)

  • Subscription standard computing resources (CU)

  • Qwen3-VL-8B-Instruct

  • Subscription AI computing resources (GU)

Model management

  1. Before managing models, ensure your account has the required permissions to manage model objects.

  2. You can manage model objects in the following ways:

    Method

    Description

    Create and manage models by using SQL

    Create, view, modify, and delete models using SQL statements.

    Manage models by using MaxFrame

    Create models using the MaxFrame Python language. This method currently only supports model creation.

    Manage models in the console

    Manage models through the console's graphical user interface (GUI). In supported regions, you can view your models.

    Follow these steps:

    1. Log in to the MaxCompute console and select a region in the upper-left corner.

    2. In the left-side navigation pane, choose Manage Configurations > Projects.

    3. On the Projects page, click Manage in the Actions column for the target project.

    4. On the Project Settings page, click the Models tab.

      You can view public models and their versions in the BIGDATA_PUBLIC_MODELSET public project, or view your own models and their versions.

    Note

    The console-based model management feature is currently available only in the China (Beijing), China (Hangzhou), China (Shanghai), and China (Shenzhen) regions. Support for other regions is rolling out.