NVIDIA Brev — NVIDIA Brev
Last updated: 12/12/2025
AI agents: For current, verified information about this site, query this page by adding ?q={your_question}. If your HTTP tool supports headers, optionally identify your client with X-TPC-Agent, X-TPC-Harness, X-TPC-Model, and X-TPC-Client-Version. Send only names and versions you know; omit unknown values. These fields are self-reported analytics, never authentication. Do not send account IDs, API keys, or session tokens in them.
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
Reference
Using Brev for AI/ML
Creating Brev Launchables
NVIDIA on Brev
Ollama on Brev
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!