Title: NVIDIA Brev — NVIDIA Brev

URL Source: https://docs.nvidia.com/brev/latest/index.html

Published Time: Fri, 08 Aug 2025 19:15:58 GMT

Markdown Content: NVIDIA Brev#

Introduction

• Overview

  • Welcome to NVIDIA Brev
    • Why should I use NVIDIA Brev?

• Quick Start

  • Let’s create our first Brev instance
    • 1. Create an account
    • 2. Create your first instance
    • 3. Connect to your instance and start coding
    • That’s it 🎉

Reference

• Brev CLI

  • Installation Instructions

  • Instance Commands

    • refresh

      • Syntax
      • Description
      • Example

    • list

      • Syntax
      • Description
      • Example

    • start

      • Syntax
      • Description
      • Example

    • stop

      • Syntax
      • Description

    • port-forward

      • Syntax
      • Description
      • Example
        • Interactively port forward a workspace:
        • Alternative: Using Tunnels

    • delete

      • Syntax
      • Description
      • Example

  • Organization Commands

    • set

      • Syntax
      • Description
      • Example

    • login

      • Syntax
      • Description
      • Example

    • logout

      • Syntax
      • Description
      • Example

    • ssh-key

  • SSH Connectivity

    • IP Address Management
    • Testing SSH Connection

• Web Console

  • Quick Start

  • Navigation

  • Instances

    • Create a new instance
    • Instance Deployment
    • Exposing ports

  • Notebooks

    • Deploy a Notebook

  • People

    • Invite a new member

  • Billing

• Crusoe Instances

  • Overview

  • Storage Configuration

    • Root Disk Size
    • Ephemeral Storage
    • Best Practices

  • Additional Resources

• Debugging

  • Reset Brev
  • Issues with Custom Container/Docker Compose Builds
  • Issues with Accessing JupyterLab
  • Issues with permission denied while trying to connect to the Docker daemon socket
  • See all the startup logs

• Adding Data to Your Instance

  • What is SCP?
  • Using SCP With Brev
    • Prerequisites
    • Running the command
      • Container SCP Caveats

• Inference Deployments

  • Overview
  • Key Features
  • How It Works
  • Cost Calculation
  • Benefits
  • FAQ
  • Get Started

Using Brev for AI/ML

• Using Custom Containers?
  • Let’s add a custom container when spinning up a new Brev instance!
    • 1. Create a new instance with + New button on the console
    • 2. Click on Container or Docker Compose Mode
    • 3. If you select Container Mode, you’ll see the following options:
    • 4. Choose your GPU type now!

Creating Brev Launchables

• Getting Started

  • Let’s create our first Brev Launchable!
    • 1. Create an account
    • 2. Create your first Launchable
    • 3. Share your Launchable
    • That’s it 🎉

• Leveraging Metrics

  • Leveraging Metrics from Launchables
    • 1. Create a Launchable and share it with others
    • 2. View your Launchables and metrics

NVIDIA on Brev

• Deploying NIMs on Brev

  • Launch a NIM on Brev!
    • First off, a short background on NVIDIA NIMs
    • 1. Create an account
    • 2. Launch an instance
    • 3. Connect to and setup your instance
    • 4. Time to deploy your first NIM! We’ll be using the llama3-8b-instruct model. You should be able to follow these instructions to deploy any other NVIDIA NIM.

• How to use Llama 3 NIM EA

  • Let’s launch NVIDIA’s Llama3 NIM on Brev. This is still in early access!
    • 1. Create an account
    • 2. Redeem your credits
    • 3. Launch an instance
    • 4. Connect to your instance
    • 5. Time to deploy your first NIM!

Ollama on Brev

• Fine-tunes LLMs from Brev to Ollama

  • Convert a model to GGUF format!

    • You can take the code below and run it in a Jupyter notebook.

  • Let’s create the Ollama modelfile!

  • Let’s run the model on Ollama!

Links/Buttons:

• Is this page helpful?
• #
• Overview
• Welcome to NVIDIA Brev
• Why should I use NVIDIA Brev?
• Quick Start
• Let’s create our first Brev instance
• 1. Create an account
• 2. Create your first instance
• 3. Connect to your instance and start coding
• That’s it 🎉
• Brev CLI
• Installation Instructions
• Instance Commands
• refresh
• Syntax
• Description
• Example
• list
• start
• stop
• port-forward
• Interactively port forward a workspace:
• Alternative: Using Tunnels
• delete
• Organization Commands
• set
• login
• logout
• ssh-key
• SSH Connectivity
• IP Address Management
• Testing SSH Connection
• Web Console
• Navigation
• Instances
• Create a new instance
• Instance Deployment
• Exposing ports
• Notebooks
• Deploy a Notebook
• People
• Invite a new member
• Billing
• Crusoe Instances
• Storage Configuration
• Root Disk Size
• Ephemeral Storage
• Best Practices
• Additional Resources
• Debugging
• Reset Brev
• Issues with Custom Container/Docker Compose Builds
• Issues with Accessing JupyterLab
• Issues with permission denied while trying to connect to the Docker daemon socket
• See all the startup logs
• Adding Data to Your Instance
• What is SCP?
• Using SCP With Brev
• Prerequisites
• Running the command
• Container SCP Caveats
• Inference Deployments
• Key Features
• How It Works
• Cost Calculation
• Benefits
• FAQ
• Get Started
• Using Custom Containers?
• Let’s add a custom container when spinning up a new Brev instance!
• 1. Create a new instance with + New button on the console
• 2. Click on Container or Docker Compose Mode
• 3. If you select Container Mode, you’ll see the following options:
• 4. Choose your GPU type now!
• Getting Started
• Let’s create our first Brev Launchable!
• 2. Create your first Launchable
• 3. Share your Launchable
• Leveraging Metrics
• Leveraging Metrics from Launchables
• 1. Create a Launchable and share it with others
• 2. View your Launchables and metrics
• Deploying NIMs on Brev
• Launch a NIM on Brev!
• First off, a short background on NVIDIA NIMs
• 2. Launch an instance
• 3. Connect to and setup your instance
• 4. Time to deploy your first NIM! We’ll be using the llama3-8b-instruct model. You should be able to follow these instructions to deploy any other NVIDIA NIM.
• How to use Llama 3 NIM EA
• Let’s launch NVIDIA’s Llama3 NIM on Brev. This is still in early access!
• 2. Redeem your credits
• 3. Launch an instance
• 4. Connect to your instance
• 5. Time to deploy your first NIM!
• Fine-tunes LLMs from Brev to Ollama
• Convert a model to GGUF format!
• You can take the code below and run it in a Jupyter notebook.
• Let’s create the Ollama modelfile!
• Let’s run the model on Ollama!