---
type: "post"
id: "the-model-that-didn-t-exist-so-you-f74bab"
slug: "the-model-that-didn-t-exist-so-you-f74bab"
title: "The model that didn't exist, so you made it yourself"
description: "Hugging Face published a case study on ML Intern, a mode in HuggingChat that can plan and run custom-model projects on Hugging Face hardware."
retrieval_nugget: "Hugging Face published a case study on ML Intern, a mode in HuggingChat that can plan and run custom-model projects on Hugging Face hardware."
published_at: "2026-10-24"
updated_at: "2026-10-24"
record_date: "2026-10-24"
date_kind: "published_at"
topics: ["agent-economics","model-routing"]
entities: ["Hugging Face","ML Intern","HuggingChat","Qwen3.5-2B","Qwen-Image 2.1","FLUX.2 klein base 4B"]
related_patterns: ["agent-economics-moves-to-completed-work","verification-bandwidth-is-the-scarce-resource"]
novelty_label: "new_fact"
what_changed: "Adds a hands-on account of using ML Intern to create and publish six small custom models, including a 0.8B CPU-running model trained for $16."
prior_refs: ["memory:c10b762b-c11e-8caf-a74a-0d166768958c"]
source_url: "https://huggingface.co/blog/building-with-ml-intern"
source_urls: ["https://huggingface.co/blog/building-with-ml-intern"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:the-model-that-didn-t-exist-so-you-f74bab"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/the-model-that-didn-t-exist-so-you-f74bab/","markdown":"https://newruntime.com/posts/the-model-that-didn-t-exist-so-you-f74bab.md","json":"https://newruntime.com/posts/the-model-that-didn-t-exist-so-you-f74bab.json"}
---

# The model that didn't exist, so you made it yourself

## Retrieval answer

Hugging Face published a case study on ML Intern, a mode in HuggingChat that can plan and run custom-model projects on Hugging Face hardware.

Hugging Face published a case study on ML Intern, a mode in HuggingChat that can plan and run custom-model projects on Hugging Face hardware. The company says the agent asks for a budget before paid jobs, runs a small test before a full run, then trains, evaluates, and publishes outputs to the Hub.

The post reports six projects with total CPU and GPU job charges of about $103. One Qwen3.5-2B citrus-disease model was fine-tuned on 3,017 annotated images: reported accuracy on 335 test photos rose from 14.9% for the base model to 52.8% after two epochs on one A10G, at about $1.90. A 0.8B prompt rewriter was trained and released as an 812 MB GGUF file for CPU use; the reported project cost was about $16.

Other examples include Qwen-Image 2.1 LoRAs, a FLUX.2 klein LoRA, and a four-step distilled image model. The source recommends specifying a baseline, a smoke test, expected deliverables, and a spending cap. It does not establish that the reported costs, quality results, or agent reliability will generalize to other datasets, models, or teams.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Agent Economics](https://newruntime.com/topics/agent-economics.md): Explore the agent-economics topic hub.
- topic hub: [Model Routing](https://newruntime.com/topics/model-routing.md): Explore the model-routing topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)