Snowflake ML

Prototype to production machine learning with distributed GPUs or CPUs on the same platform as your governed data. Streamline model development and MLOps with no infrastructure to maintain or configure – all through a centralized UI.

Efficient

Large-scale data processing for model development directly within Snowflake's platform, eliminating the need for data movement

Easy

ML workflows using any Python library and framework or low-code SQL functions with no infrastructure to configure or maintain

Trusted

Discover, manage, use, and govern ML features and models in Snowflake across the entire ML lifecycle with end-to-end lineage

Screenshot of Snowflake Notebooks using Streamlit to visualize data in a line graph

Scalable Model Development

Easily build models training with distributed GPUs or CPUs from Snowflake Notebooks on Container Runtime. Leverage pre-installed popular libraries such as XGBoost and PyTorch or pip install any package from open source hubs such as PyPi and HuggingFace.

Continuously Updated ML Features

Create, manage, and serve ML features with continuous, automated refresh on batch or streaming data using the Snowflake Feature Store.

Screenshot of the Features Dashboard on the Snowflake platform
Screenshot of the ML Models dashboard on Snowflake

Flexible Model Inference

Serve models for production with distributed GPUs or CPUs from the Snowflake Model Registry, including support for models trained on external platforms. Easily monitor performance and drift metrics2.

watch the video

Explore more related features:

Tab 1

Tab 2

Tab 3

Quote Icon

Bringing familiar modeling capabilities to Snowflake ML has enabled us to more rapidly iterate on our models, improving accuracy and operational efficiency

SVP of Engineering at Decile
Quote Icon

Using Snowflake ML, we've been able to achieve a 70% cost reduction and enhanced agility by moving from running hour-long inference jobs to predictions in near real-time.

CTO, Paytronix
Quote Icon

We can more easily build predictive models and mock up data products all in the Snowflake ecosystem because the data is all there.

Manager of Data Science, IGS Energy
Pages from a Snowflake PDF asset layered on top of a blue background
ON-DEMAND WEBINAR

Technical Deep Dive: How CHG Healthcare Builds Faster XGBoost Models

SNOWFLAKE ML ARCHITECTURE

snowflake ML diagram
LEADING BRANDS LEVERAGE SNOWFLAKE ML

Start your 30-DayFree Trial

Try Snowflake free for 30 days and experience the AI Data Cloud that helps eliminate the complexity, cost and constraints inherent with other solutions. 

1Private preview

2Public preview

3Only available in select regions. See documentation for full program details.