# modal-labs/modal-examples

Examples of programs built using Modal

Repository: https://github.com/modal-labs/modal-examples
Canonical: https://ross.abutalabs.com/products/modal-examples
Homepage: https://modal.com/docs
Language: Python
License: MIT
License Family: permissive
Topics: cloud, machine-learning, modal, python, serverless, distributed, gpu, pytorch, stable-diffusion, web
Last push: 2026-09-02T23:38:00+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 35, longevity 100
- inputs: {"age_days": 1470, "days_push": 0, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1264, forks 317 (observed 2026-09-03T02:15:15.172178+00:00)

## What it is
A curated collection of example programs for Modal, a serverless cloud platform, covering use cases like LLM serving, image generation, speech transcription, and computational biology. The examples serve as both tutorials for learning Modal and starting points for building scalable GPU-accelerated applications.

## Use cases
- learn how to deploy code on modal serverless cloud
- run llm inference on gpus without managing infrastructure
- deploy stable diffusion or flux image generation as an api
- batch transcribe audio with whisper at scale
- fine-tune llms or image models in the cloud
- run coding agents in secure sandboxes
- spin up serverless gpu jobs for machine learning workloads

## When to choose
- you are learning the Modal platform and want tested, runnable examples
- you need reference code for deploying ML models on serverless GPU infrastructure
- you want a starting template for LLM serving, fine-tuning, or batch processing on Modal

## When to avoid
- you are not using the Modal platform and want a general-purpose ML library
- you need production software rather than example/tutorial code
- you want to run compute on your own infrastructure instead of Modal's cloud

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, llm-inference, gpu-computing, serverless, cloud, speech-recognition, stable-diffusion, web-scraping
- domain: cloud-computing, machine-learning, developer-tools, gpu-computing, large-language-models, tutorials
- platform: python, cloud
- tags: modal, examples, serverless-gpu, sample-code, documentation-examples, docker, gpu

## Member repositories
- modal-labs/modal-examples (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:15.172178+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:04:14.515714+00:00, confidence not recorded.
  - readme: https://github.com/modal-labs/modal-examples (fetched 2026-09-03T02:15:15.172178+00:00, sha 689da5cde679)
  - homepage: https://modal.com/docs (fetched 2026-08-29T12:16:55.997975+00:00, sha ad435e260a3a)
  - site_page: https://modal.com/docs/examples/esmfold2_binder_design (fetched 2026-08-29T12:16:56.019366+00:00, sha 26b24aa96754)
  - site_page: https://modal.com/docs/examples/batched_whisper (fetched 2026-08-29T12:16:56.021334+00:00, sha e1a8197a2bde)
  - site_page: https://modal.com/docs/guide (fetched 2026-08-29T12:16:56.007204+00:00, sha 318f658a9f8c)
  - site_page: https://modal.com/docs/examples (fetched 2026-08-29T12:16:56.009317+00:00, sha 24dbde805117)
  - site_page: https://modal.com/docs/sdk/py/latest (fetched 2026-08-29T12:16:56.011190+00:00, sha df9e316267bb)
  - site_page: https://modal.com/docs/examples/llm_inference (fetched 2026-08-29T12:16:56.012939+00:00, sha 44136fa355b3)
  - site_page: https://modal.com/docs/examples/vllm_throughput (fetched 2026-08-29T12:16:56.014761+00:00, sha 66887a97a381)
  - site_page: https://modal.com/docs/examples/opencode_server (fetched 2026-08-29T12:16:56.017408+00:00, sha 0c858c9da497)
- Data as of 2026-08-30T08:39:29.467469+00:00.