> ## Documentation Index
> Fetch the complete documentation index at: https://docs.beam.cloud/llms.txt
> Use this file to discover all available pages before exploring further.

# Examples

> End-to-end examples for running real workloads on Beam

Browse complete, runnable examples grouped by what you're building. Each one shows a real workload, from container image to deployment, that you can copy and adapt.

New to Beam? Start with the [Quickstart](/v2/getting-started/quickstart) and [Core Concepts](/v2/getting-started/core-concepts) first.

## Large Language Models

Serve and run inference with open and custom LLMs.

<CardGroup cols={2}>
  <Card title="Hugging Face Models" icon="bolt" href="/v2/examples/inference">
    A beginner's guide to running performant inference workloads on Beam.
  </Card>

  <Card title="LLaMA 3.1 8B" icon="comments" href="/v2/examples/llama3">
    Serve Meta's LLaMA 3.1 8B model on a GPU.
  </Card>

  <Card title="Run an OpenAI-Compatible vLLM Server" icon="server" href="/v2/examples/vllm">
    Host an OpenAI-compatible inference server with vLLM.
  </Card>

  <Card title="Chat with DeepSeek R1" icon="comment-dots" href="/v2/examples/deepseek-r1">
    Run the DeepSeek R1 reasoning model.
  </Card>

  <Card title="Qwen2.5-7B with SGLang" icon="gauge" href="/v2/examples/sglang">
    Serve Qwen2.5-7B with the SGLang runtime.
  </Card>
</CardGroup>

## Image and Video

Generate and transform images and video on GPUs.

<CardGroup cols={2}>
  <Card title="Serverless ComfyUI" icon="image" href="/v2/examples/comfy-ui">
    Host ComfyUI for image generation workflows.
  </Card>

  <Card title="Text-to-Video with Mochi" icon="film" href="/v2/examples/mochi-1">
    Generate video from text with the Mochi model.
  </Card>

  <Card title="Stable Diffusion with LoRAs" icon="wand-magic-sparkles" href="/v2/examples/lora">
    Run Stable Diffusion with custom LoRA adapters.
  </Card>
</CardGroup>

## Audio and Transcription

Transcribe and synthesize speech.

<CardGroup cols={2}>
  <Card title="Faster Whisper" icon="microphone" href="/v2/examples/whisper">
    Transcribe audio with Faster Whisper.
  </Card>

  <Card title="Parler TTS" icon="volume-high" href="/v2/examples/parler-tts">
    Synthesize speech with Parler TTS.
  </Card>

  <Card title="Zonos" icon="music" href="/v2/examples/zonos">
    Generate speech with the Zonos model.
  </Card>
</CardGroup>

## Web Apps

Host interactive apps and scrape the web.

<CardGroup cols={2}>
  <Card title="Web Scraping with Beam Functions" icon="spider" href="/v2/examples/web-scraping">
    Build a web scraper that runs on Beam functions.
  </Card>

  <Card title="Running Streamlit Apps" icon="chart-line" href="/v2/examples/streamlit">
    Host a Streamlit app behind a public URL.
  </Card>
</CardGroup>

## Agents

Build and coordinate AI agents.

<CardGroup cols={2}>
  <Card title="Building AI Agents" icon="robot" href="/v2/agents/introduction">
    Build stateful agents with concurrency built in.
  </Card>

  <Card title="Research Assistant" icon="magnifying-glass" href="/v2/agents/synchronization">
    A research assistant that synchronizes state across tasks.
  </Card>
</CardGroup>

## Fine-Tuning

Fine-tune open models on GPUs.

<CardGroup cols={2}>
  <Card title="Fine-tuning Gemma with LoRA" icon="dumbbell" href="/v2/examples/gemma-fine-tune">
    Fine-tune Google's Gemma model with LoRA.
  </Card>

  <Card title="Fine-Tuning Llama 3.1 8B with Unsloth" icon="gauge-high" href="/v2/examples/unsloth">
    Fast fine-tuning of Llama 3.1 8B with Unsloth.
  </Card>
</CardGroup>