Skip to main content
Prime Intellect Docs home page
Search...
⌘K
Support
Platform
Platform
Search...
Navigation
Run DistillKit
Documentation
API Reference
CLI Reference
Discord
Twitter
Blog
Getting Started
Introduction
Quickstart - Deploy a Pod
FAQ
On-Demand Cloud
Run Jupyter Notebooks
Deploy Llama via VLLM
Deploy Custom Docker Image
Storage
Create persistent storage
Use persistent storage with instances
Cluster storage
Multi-Node Clusters
Deploy Multi-Node Cluster
Slurm Orchestration
Run Torch FSDP
Llama 405B Inference in BF16
Environment Hub
Overview
Getting Started
Create & Upload Environment
Install & Use Environment
Evaluating Environments (Closed Beta)
Environment Actions
Manage Collaborators
Inference (Closed Beta)
Inference Overview
Advanced Usage
Using Team Accounts
Reinforcement Fine-Tuning
Reinforcement Fine-Tuning (Beta)
Sandboxes
Sandboxes Overview
Sandbox CLI Guide
Sandbox SDK Guide
Community Pools
Contribute Compute
Contribution Guidelines
Contribution FAQ
Run DistillKit
Distill Llama 405B into smaller models via our Multi-node offering.
This tutorial for running DistillKit on multi-node clusters is currently in development. Please check back soon for detailed instructions on model distillation at scale.
⌘I