HF

ML Intern

AI agent

by Hugging Face

Mode in HuggingChat that plans and runs machine-learning work from a plain-language request: reads papers, models and datasets, writes scripts, runs them on Hugging Face compute, and can reproduce a paper, finetune and evaluate a model, curate a dataset or deploy a demo Space.

Find alternatives to ML Intern

What it does

• Model training
• Agentic coding

Sources

Pricing

Official documentation · 18 Oct 2026

"Credits for compute. ML Intern runs Hugging Face Jobs and sandboxes, billed to your Hugging Face credits"; "Chatting with the model is billed separately, as Inference Providers usage."; "Every ML Intern conversation has its own compute budget ... It starts at $0".

Description

Official documentation · 18 Oct 2026

"Describe a task in plain language and ML Intern reads the relevant papers, models and datasets, writes the scripts, runs them on Hugging Face compute, and reports back."

What it does

Official documentation · 18 Oct 2026

"reproduce a paper at small scale; finetune a model and evaluate the checkpoint; generate or curate a dataset and push it to the Hub; build a demo and deploy it as a Space; run a model against a benchmark"

Sold within

Not found · 18 Oct 2026

The page says it is a mode in HuggingChat and needs a Hugging Face account and credits; it states no plan that includes or excludes it.

Name

Official documentation · 18 Oct 2026

"ML Intern is a mode in HuggingChat that plans and runs machine-learning work for you, using the Hugging Face Hub as its workspace."

URL

Official documentation · 18 Oct 2026

The mode's own documentation page, "Getting started with ML Intern"; the HuggingChat page announces it.

Deployment

Official documentation · 18 Oct 2026

"runs them on Hugging Face compute"; "ML Intern runs Hugging Face Jobs and sandboxes, billed to your Hugging Face credits or to an organization you belong to".

Interfaces

Official documentation · 18 Oct 2026

"Go to huggingface.co/chat and sign in with your Hugging Face account. In a new conversation, turn on the ML Intern switch under the message box."

Also from Hugging Face

• Hugging Face Hub Platform

  Hosts and versions open models, datasets and demo applications, publicly or privately.

• Inference Endpoints Infrastructure service

  Deploys a model from the Hub to a dedicated managed endpoint, billed by the hour.

• Spaces Platform

  Hosts runnable demo applications for models on free or paid hardware.

• HuggingChat Application

  Chat app powered by open-source AI models with an Omni router that automatically selects the most suitable model, or lets users pick directly from over 100 open models.

• Inference Providers API service

  Marketplace connecting users to multiple third-party inference providers for hosted AI models, billed per input/output token with provider- and model-specific rates shown side by side.

• Hugging Face Jobs Infrastructure service

  Pay-as-you-go compute for running AI training, fine-tuning, synthetic data generation and batch inference jobs on Hugging Face's own CPU/GPU/TPU infrastructure via CLI or Python API.

• Storage Buckets Infrastructure service

  Object storage for AI teams to hold models, datasets, checkpoints and artifacts, with per-TB pricing, Xet deduplication and a built-in CDN, without git overhead.

• AutoTrain Platform

  AutoTrain provides a no-code interface for training machine learning models.

Open Hugging Face in the directory

Something wrong here? Send a correction — quote this product id: huggingface-ml-intern.