--- title: TabFM adds predictive ML to BigQuery | daily.dev description: Google Cloud introduces TabFM, a pre-trained foundation model for tabular data now available in preview within BigQuery. Using in-context learning similar to... canonical: https://daily.dev/posts/tabfm-adds-predictive-ml-to-bigquery-hvyqkh6fv twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: TabFM adds predictive ML to BigQuery | daily.dev og:description: Google Cloud introduces TabFM, a pre-trained foundation model for tabular data now available in preview within BigQuery. Using in-context learning similar to... og:url: https://daily.dev/posts/tabfm-adds-predictive-ml-to-bigquery-hvyqkh6fv og:image: https://api.daily.dev/og/posts/hvYQkH6Fv.png og:image:alt: TabFM adds predictive ML to BigQuery og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # TabFM adds predictive ML to BigQuery **[Google Cloud](https://daily.dev/sources/gcp)** · 5 min read · 0 upvotes · 0 comments ## Summary Google Cloud introduces TabFM, a pre-trained foundation model for tabular data now available in preview within BigQuery. Using in-context learning similar to LLMs, TabFM delivers zero-shot regression and classification predictions directly through new SQL functions, AI.PREDICT and AI.EVALUATE, without requiring model training, tuning, or deployment. It claims state-of-the-art accuracy on the TabArena benchmark, scales to millions of inference rows via BigQuery's distributed architecture, and is positioned as complementary to traditional approaches like XGBoost, which remain preferable for very large datasets or when feature-importance explainability is required. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is TabFM in BigQuery and how do I use it to make predictions with SQL? TabFM is a pre-trained foundation model for tabular regression and classification, now available in preview in BigQuery. It uses in-context learning to generate predictions directly from a single SQL statement via the AI.PREDICT function, passing a historical training table and a new prediction table, with no separate model training or deployment step required. _See how daily.dev surfaces new BigQuery ML capabilities like this for teams evaluating predictive analytics tools._ ### When should I use TabFM instead of XGBoost for predictive modeling in BigQuery? TabFM works best for rapid, zero-shot predictions without machine learning expertise, small-to-medium historical datasets, frequently changing data, or conversational and agentic workflows needing on-demand predictions. XGBoost remains preferable for very large datasets, full control over hyperparameter tuning, feature counts exceeding TabFM's limits, or when feature-importance explainability is required. _Developers weighing tabular ML tools can track comparisons like this on daily.dev before committing to one._ ### How do I evaluate a BigQuery TabFM model's prediction accuracy? Use the AI.EVALUATE SQL function, passing a historical training table and a test table with a specified label column. It returns standard metrics automatically: r2_score and mean_absolute_error for regression tasks, and precision, recall, and f1 for classification tasks, without needing to build a separate evaluation pipeline. _daily.dev helps engineers stay current on SQL-native ML evaluation workflows like this one._ ## Similar posts on daily.dev - [TimesFM models in BigQuery and AlloyDB](https://daily.dev/posts/timesfm-models-in-bigquery-and-alloydb-haojhbaki) · Google Cloud · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#sql](https://daily.dev/tags/sql), [#gcp](https://daily.dev/tags/gcp), [#google-bigquery](https://daily.dev/tags/google-bigquery), [#predictive-analytics](https://daily.dev/tags/predictive-analytics) [View this post on daily.dev](https://daily.dev/posts/tabfm-adds-predictive-ml-to-bigquery-hvyqkh6fv) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"TabFM adds predictive ML to BigQuery","url":"https://daily.dev/posts/tabfm-adds-predictive-ml-to-bigquery-hvyqkh6fv","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/tabfm-adds-predictive-ml-to-bigquery-hvyqkh6fv"},"datePublished":"2026-09-01T16:07:12.307Z","dateModified":"2026-09-02T15:46:08.129Z","description":"Google Cloud introduces TabFM, a pre-trained foundation model for tabular data now available in preview within BigQuery. Using in-context learning similar to...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9df795f90d3290a29c3b5ccad1c3e312?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9df795f90d3290a29c3b5ccad1c3e312?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Google Cloud","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Google Cloud","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/gcp","url":"https://daily.dev/sources/gcp"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/tabfm-adds-predictive-ml-to-bigquery-hvyqkh6fv","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,sql,gcp,google-bigquery,predictive-analytics","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Google Cloud","item":"https://daily.dev/sources/gcp"},{"@type":"ListItem","position":3,"name":"TabFM adds predictive ML to BigQuery"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/tabfm-adds-predictive-ml-to-bigquery-hvyqkh6fv#faq","mainEntity":[{"@type":"Question","name":"What is TabFM in BigQuery and how do I use it to make predictions with SQL?","acceptedAnswer":{"@type":"Answer","text":"TabFM is a pre-trained foundation model for tabular regression and classification, now available in preview in BigQuery. It uses in-context learning to generate predictions directly from a single SQL statement via the AI.PREDICT function, passing a historical training table and a new prediction table, with no separate model training or deployment step required. See how daily.dev surfaces new BigQuery ML capabilities like this for teams evaluating predictive analytics tools."}},{"@type":"Question","name":"When should I use TabFM instead of XGBoost for predictive modeling in BigQuery?","acceptedAnswer":{"@type":"Answer","text":"TabFM works best for rapid, zero-shot predictions without machine learning expertise, small-to-medium historical datasets, frequently changing data, or conversational and agentic workflows needing on-demand predictions. XGBoost remains preferable for very large datasets, full control over hyperparameter tuning, feature counts exceeding TabFM's limits, or when feature-importance explainability is required. Developers weighing tabular ML tools can track comparisons like this on daily.dev before committing to one."}},{"@type":"Question","name":"How do I evaluate a BigQuery TabFM model's prediction accuracy?","acceptedAnswer":{"@type":"Answer","text":"Use the AI.EVALUATE SQL function, passing a historical training table and a test table with a specified label column. It returns standard metrics automatically: r2_score and mean_absolute_error for regression tasks, and precision, recall, and f1 for classification tasks, without needing to build a separate evaluation pipeline. daily.dev helps engineers stay current on SQL-native ML evaluation workflows like this one."}}]} ```