Hello, world Simple web scraper Serving web endpoints Deploy an OpenAI-compatible LLM service with vLLM Cut Ministral 3 cold start times by 10x with snapshots Maximize tokens per second in batch processing with vLLM Serve an ultra-low-latency chatbot with SGLang Efficient LLM Finetuning with Unsloth Run a multimodal RAG chatbot to answer questions about PDFs Fine-tune an LLM to replace your CEO Deploy a stateless MCP with FastMCP Edit images with Flux Kontext Fine-tune Wan2.1 video models on your face Run Flux fast with torch.compile Fine-tune Flux with LoRA Animate images with LTX-Video Generate video clips with LTX-Video Run Stable Diffusion with a CLI, API, and web UI Deploy a Moshi voice chatbot Stream transcripts at the speed of speech using Kyutai STT Make music with ACE-Step Generate speech with Chatterbox Run high throughput batched transcription with Whisper Fine-tune Whisper to recognize new words Serverless WebRTC WebRTC quickstart with FastRTC Fold proteins with Chai-1 Build a protein-folding dashboard Fold proteins with Boltz-2 Run a background coding agent with OpenCode Build a scalable AI coding platform Run a LangGraph agent's code in a secure GPU sandbox Control a sandboxed computer with an LLM Build a stateful, sandboxed code interpreter Run Node.js, Ruby, and more in a Sandbox Run a sandboxed Jupyter notebook Train a model to solve math problems using GRPO and verl Train a model to solve coding problems using GRPO and TRL Embed millions of documents with TEI Turn satellite images into vectors and store them in MongoDB Deploy a Hacker News Slackbot Run a Document OCR job queue Serve a Document OCR web app Train an SLM with early-stopping grid search over hyperparameters Run long, resumable training jobs YOLO: Fine-tune and serve computer vision models Blender: Build a 3D render farm Streamlit: Run and deploy Streamlit apps ComfyUI: Run Flux on ComfyUI as an API SQLite: Publish explorable data with Datasette Algolia: Build docsearch with a crawler Discord: Deploy and run a Discord Bot Google Sheets: Sync databases and APIs to a Google Sheet OpenAI: Run a RAG Q&A chatbot Tailscale: Add Modal Apps to your VPN Prometheus: Publish custom metrics with Pushgateway Mount S3 buckets in Modal apps Build your own data warehouse with DuckDB, DBT, and Modal Create a LoRA Playground with Modal, Gradio, and S3

Snapshot GPU memory to speed up cold starts

This example demonstrates how to use GPU memory snapshots to speed up model loading. Note that GPU memory snapshotting is an experimental feature, so test carefully before using in production! You can read more about GPU memory snapshotting, and its caveats, here.

GPU snapshots can only be used with deployed Functions, so first deploy the App:

Next, invoke the Function:

The full code is below:

Try this on Modal!

You can run this example on Modal in 60 seconds.

Create account to run

After creating a free account, install the Modal Python package, and create an API token.

Clone the modal-examples repository and run: