HearthNet / docs /guides /fieldguide.md
GitHub Actions
feat(rag): docs ingestion + UI/bus enhancements (P3 continuation)
f08047d
|
Raw
History Blame Contribute Delete
15.8 kB
Build Small
the idea
tracks
## Build Small
the idea
tracks
rules
prizes
find your kit
partners
submit
faq
**Submit**
Hugging Face × Gradio
N 45.21 · W 122.6
## BUILD SMALL
Build something small, local, and yours.
Registration’s closed and the jam is underway — this is your field guide. Everything you need to enter cleanly: the rules, the 29 ways to win, and the right kit for what you’re building.
See the prizes
Resources
June 15, 2026
final deadline
≤ 32B
params, max
$48k+
prize pool
29
ways to win
## The big idea
The future of AI doesn’t have to live in someone else’s data center.
Build Small is a return to small, local, tinkerable models. Open weights you can read, run and reshape — everything under 32B parameters, humming away on hardware you actually own. Less API bill, more workshop.
## 02 · Pick a trail
### Two tracks, one campsite
Solve a real problem, or wander somewhere weird. Both are equally celebrated — and carry the same prize pool.
### THE PRACTICAL TRACK
#### Backyard AI
Practical, problem-solving apps built to improve daily life — for you or someone close to you. Useful things that run on hardware you own.
- A custom storybook generator for a child
- A personal study tutor
- A receipt or bill parser
- An on-device document assistant
### THE WHIMSICAL TRACK
#### Thousand Token Wood
Whimsical, delightful, AI-native apps that push the boundaries of fun. Wander somewhere stranger and show off what small models can dream up.
- Interactive AI games
- Out-of-the-box entertainment tools
- A desktop pet that lives on your machine
- A text-adventure dungeon master
## 03 · Trail rules
### Entry criteria at a glance
The things every submission needs. Tick them off and you’re on the board.
#### REQ-01 · Stay under 32B
Every model must be under 32B parameters. Combine several small models if you like — but each one’s total parameter count must stay below the cap.
#### REQ-02 · Ship a Gradio app
Deploy your project as a Gradio App inside the official Build Small org on Hugging Face. Docker is fine, as long as the interface is a Gradio Space.
#### REQ-03 · Record a demo
Submit a demo video showing your app working — so judges can evaluate it even if GPU or API limits stop a live run.
#### REQ-04 · Post it
Create one social-media post showcasing your app, and link to it from your Space README.
#### REQ-05 · Mind the GPU limit
Submit as many apps as you like. If you rely on the provided Zero GPU resources, you’re limited to 10 Zero GPU apps per user.
#### REQ-06 · Tag your README
Add tags for the tracks and badges you want to be considered for to the yaml block at the top of your README, plus a short write-up of the idea and tech.
## 04 · The prize table
### 29 ways to win
A $48k cash pool plus 20k Modal credits, two NVIDIA RTX GPUs and ChatGPT Pro — across track placements, sponsor challenges, and collectable bonus badges.
$48k
cash pool
+29
ways to win
All prizes
General
Sponsor prizes
Bonus badges
### GENERAL TRACK PRIZES · AWARDED PER TRACK
#### Backyard AI
- 1st — $4,000
- 2nd — $2,500
- 3rd — $1,500
- 4th — $1,000
- Community Choice — $2,000
#### Thousand Token Wood
- 1st — $4,000
- 2nd — $2,500
- 3rd — $1,500
- 4th — $1,000
- Community Choice — $2,000
### SPONSOR PRIZES · OWN CRITERIA PER PRIZE
#### OpenBMB · Best MiniCPM Build
- 1st — $2,500
- 2nd — $1,500
- 3rd — $1,000
- To qualify ·Build with MiniCPM models.
- Clarifications (3)
#### OpenAI · Best Use of Codex
- 1st — $5,000
- 2nd — $3,000
- 3rd — $1,000
- To qualify ·Requires Codex-attributed commits in your connected GitHub repo or Space.
- Clarifications (2)
#### NVIDIA · Nemotron Hardware Prize
- Best space — RTX 5080
- Community engagement — RTX 5080
- To qualify ·Build with Nemotron models.
- Clarifications (2)
#### Modal · Best Use of Modal
- 1st — 10,000 credits
- 2nd — 7,000 credits
- 3rd — 3,000 credits
- To qualify ·Use Modal for the development or runtime of your app, and note it in your Space README.
- Clarifications (2)
### BONUS BADGES · TAP FOR DETAILS
#### $1,500 · Off Brand
The best custom UI that pushes past the default Gradio look.
What counts
#### $1,500 · Tiny Titan
The best app built on a genuinely tiny model.
What counts
#### $1,000 · Best Demo
The full package: great app, great demo video, great social post.
What counts
#### $1,000 · Best Agent
The best agentic app.
What counts
#### $2,000 · Bonus Quest Champion
The most bonus criteria met across the board.
What counts
#### $1,000 · Judges’ Wildcard
For the entry that’s amazing but fits no category.
What counts
## 05 · Choose your kit
### What are you building?
Tell us the shape of your idea and we’ll point you at the partners and models worth reaching for. Then dig into their pages for the full guide.
1. Image / OCR app
2. Voice / audio app
3. Tiny text assistant
4. Coding agent
5. Need compute / training
For a image / ocr app, reach for:
Read documents, understand photos, or generate & edit images.
#### OpenBMB · MiniCPM-V 4.6
via OpenBMB
Vision-language at ~1.3B — strong OCR & document understanding.
Open
#### Black Forest Labs · FLUX.2 Klein
via Black Forest Labs
Generate and edit images locally at 4B / 9B.
Open
#### NVIDIA · Nemotron Parse
via NVIDIA
Sub-1B structured extraction from complex documents.
Open
## 06 · The outfitters
### Seven partners stocked the shed
Models, tools and compute from across the small-AI world. Tap any one for its full kit and support channels.
#### OpenBMB
MiniCPM family — tiny, capable text · vision · audio · omni models (1B–8B).
1B–8B models
#### Black Forest Labs
FLUX.2 Klein — text-to-image & precise image editing at 4B / 9B.
image gen
#### OpenAI · Codex
Codex coding agent (GPT-5.5) with GitHub, Figma & Hugging Face plugins.
coding agent
#### NVIDIA
Nemotron 3 family — Nano · Omni · ASR · Parse · Embed.
model suite
#### Modal
Serverless compute for inference, training, batch & sandboxes.
compute
#### JetBrains
Mellum 2 — 12B MoE coding models, Thinking & Instruct.
12B MoE
#### Cohere Labs
Cohere Transcribe (ASR) and Tiny Aya multilingual models.
ASR · multilingual
FIND THE RIGHT ONE
Use the kit recommender →
## 07 · The trail map
### How to submit
The markers between you and the finish line.
1. **Meet the criteria**
Double-check your build satisfies the entry rules and any prize criteria you’re targeting.
2. **Join the org**
Join the Build Small hackathon organisation on Hugging Face — your home base for the jam.
3. **Upload your Space**
Upload your submission as a Gradio Space inside the org.
4. **Record a demo**
Film a demo selling your Space — no humility. Put it on YouTube, upload it to the Space, or host it publicly.
5. **Post on social**
Share one post about your build on social media.
6. **Update your README**
Add links to the post and demo video, tags for tracks + badges in the yaml block at the top, and a short write-up of the idea and tech.
Start your submission
## 08 · Field notes
### Frequently asked
**What does “under 32B” actually mean?**
Every model your project depends on must have under 32B total parameters (not just active parameters). You can freely combine several models — say a 14B text model, a 7B speech model, and a 12B image model — as long as each one individually stays under the cap.
- Do I have to use a sponsor’s model?
- Do I need to exclusively use a sponsor’s models to win their prize?
- Am I eligible for the OpenAI Codex prize if I didn’t get free Codex credits?
- Is there a GPU limit?
- Can I use a hosted API instead of running locally?
- Can one project win multiple prizes?
- Can I submit multiple apps?
- How do I submit?
---
## BUILD SMALL
Build something small, local, and yours. A Hugging Face × Gradio hackathon.
### EXPLORE
- The idea
- Tracks
- Prizes
- Partners
### TAKE PART
- Rules
- Find your kit
- Submit
- FAQ
### ELSEWHERE
- HF Org
- Gradio
- Hugging Face
- X / Twitter
© 2026 Build Small · made small with love
≤ 32B params · open weights · run it yourself
Submit
Hugging Face × Gradio
N 45.21 · W 122.6
BUILD SMALL
Build something small, local, and yours.
Registration’s closed and the jam is underway — this is your field guide. Everything you need to enter cleanly: the rules, the 29 ways to win, and the right kit for what you’re building.
See the prizes
Resources
June 15, 2026
final deadline
≤ 32B
params, max
$48k+
prize pool
29
ways to win
The big idea
The future of AI doesn’t have to live in someone else’s data center.
Build Small is a return to small, local, tinkerable models. Open weights you can read, run and reshape — everything under 32B parameters, humming away on hardware you actually own. Less API bill, more workshop.
02
Pick a trail
Two tracks, one campsite
Solve a real problem, or wander somewhere weird. Both are equally celebrated — and carry the same prize pool.
THE PRACTICAL TRACK
Backyard AI
Practical, problem-solving apps built to improve daily life — for you or someone close to you. Useful things that run on hardware you own.
A custom storybook generator for a child
A personal study tutor
A receipt or bill parser
An on-device document assistant
THE WHIMSICAL TRACK
Thousand Token Wood
Whimsical, delightful, AI-native apps that push the boundaries of fun. Wander somewhere stranger and show off what small models can dream up.
Interactive AI games
Out-of-the-box entertainment tools
A desktop pet that lives on your machine
A text-adventure dungeon master
03
Trail rules
Entry criteria at a glance
The things every submission needs. Tick them off and you’re on the board.
REQ-01
Stay under 32B
Every model must be under 32B parameters. Combine several small models if you like — but each one’s total parameter count must stay below the cap.
REQ-02
Ship a Gradio app
Deploy your project as a Gradio App inside the official Build Small org on Hugging Face. Docker is fine, as long as the interface is a Gradio Space.
REQ-03
Record a demo
Submit a demo video showing your app working — so judges can evaluate it even if GPU or API limits stop a live run.
REQ-04
Post it
Create one social-media post showcasing your app, and link to it from your Space README.
REQ-05
Mind the GPU limit
Submit as many apps as you like. If you rely on the provided Zero GPU resources, you’re limited to 10 Zero GPU apps per user.
REQ-06
Tag your README
Add tags for the tracks and badges you want to be considered for to the yaml block at the top of your README, plus a short write-up of the idea and tech.
04
The prize table
29 ways to win
A $48k cash pool plus 20k Modal credits, two NVIDIA RTX GPUs and ChatGPT Pro — across track placements, sponsor challenges, and collectable bonus badges.
$48k
cash pool
+29
ways to win
All prizes
General
Sponsor prizes
Bonus badges
GENERAL TRACK PRIZES · AWARDED PER TRACK
Backyard AI
1st
$4,000
2nd
$2,500
3rd
$1,500
4th
$1,000
Community Choice
$2,000
Thousand Token Wood
1st
$4,000
2nd
$2,500
3rd
$1,500
4th
$1,000
Community Choice
$2,000
SPONSOR PRIZES · OWN CRITERIA PER PRIZE
OpenBMB
Best MiniCPM Build
1st
$2,500
2nd
$1,500
3rd
$1,000
To qualify ·Build with MiniCPM models.
Clarifications (3)
OpenAI
Best Use of Codex
1st
$5,000
2nd
$3,000
3rd
$1,000
To qualify ·Requires Codex-attributed commits in your connected GitHub repo or Space.
Clarifications (2)
NVIDIA
Nemotron Hardware Prize
Best space
RTX 5080
Community engagement
RTX 5080
To qualify ·Build with Nemotron models.
Clarifications (2)
Modal
Best Use of Modal
1st
10,000 credits
2nd
7,000 credits
3rd
3,000 credits
To qualify ·Use Modal for the development or runtime of your app, and note it in your Space README.
Clarifications (2)
BONUS BADGES · TAP FOR DETAILS
$1,500
Off Brand
The best custom UI that pushes past the default Gradio look.
What counts
$1,500
Tiny Titan
The best app built on a genuinely tiny model.
What counts
$1,000
Best Demo
The full package: great app, great demo video, great social post.
What counts
$1,000
Best Agent
The best agentic app.
What counts
$2,000
Bonus Quest Champion
The most bonus criteria met across the board.
What counts
$1,000
Judges’ Wildcard
For the entry that’s amazing but fits no category.
What counts
05
Choose your kit
What are you building?
Tell us the shape of your idea and we’ll point you at the partners and models worth reaching for. Then dig into their pages for the full guide.
01
Image / OCR app
02
Voice / audio app
03
Tiny text assistant
04
Coding agent
05
Need compute / training
For a image / ocr app, reach for:
Read documents, understand photos, or generate & edit images.
OpenBMB
MiniCPM-V 4.6
via OpenBMB
Vision-language at ~1.3B — strong OCR & document understanding.
Open
Black Forest Labs
FLUX.2 Klein
via Black Forest Labs
Generate and edit images locally at 4B / 9B.
Open
NVIDIA
Nemotron Parse
via NVIDIA
Sub-1B structured extraction from complex documents.
Open
06
The outfitters
Seven partners stocked the shed
Models, tools and compute from across the small-AI world. Tap any one for its full kit and support channels.
OpenBMB
MiniCPM family — tiny, capable text · vision · audio · omni models (1B–8B).
1B–8B models
Black Forest Labs
FLUX.2 Klein — text-to-image & precise image editing at 4B / 9B.
image gen
OpenAI · Codex
Codex coding agent (GPT-5.5) with GitHub, Figma & Hugging Face plugins.
coding agent
NVIDIA
Nemotron 3 family — Nano · Omni · ASR · Parse · Embed.
model suite
Modal
Serverless compute for inference, training, batch & sandboxes.
compute
JetBrains
Mellum 2 — 12B MoE coding models, Thinking & Instruct.
12B MoE
Cohere Labs
Cohere Transcribe (ASR) and Tiny Aya multilingual models.
ASR · multilingual
FIND THE RIGHT ONE
Use the kit recommender →
07
The trail map
How to submit
The markers between you and the finish line.
1
Meet the criteria
Double-check your build satisfies the entry rules and any prize criteria you’re targeting.
2
Join the org
Join the Build Small hackathon organisation on Hugging Face — your home base for the jam.
3
Upload your Space
Upload your submission as a Gradio Space inside the org.
4
Record a demo
Film a demo selling your Space — no humility. Put it on YouTube, upload it to the Space, or host it publicly.
5
Post on social
Share one post about your build on social media.
6
Update your README
Add links to the post and demo video, tags for tracks + badges in the yaml block at the top, and a short write-up of the idea and tech.
Start your submission
08
Field notes
Frequently asked
What does “under 32B” actually mean?
Every model your project depends on must have under 32B total parameters (not just active parameters). You can freely combine several models — say a 14B text model, a 7B speech model, and a 12B image model — as long as each one individually stays under the cap.
Do I have to use a sponsor’s model?
Do I need to exclusively use a sponsor’s models to win their prize?
Am I eligible for the OpenAI Codex prize if I didn’t get free Codex credits?
Is there a GPU limit?
Can I use a hosted API instead of running locally?
Can one project win multiple prizes?
Can I submit multiple apps?
How do I submit?
BUILD SMALL
Build something small, local, and yours. A Hugging Face × Gradio hackathon.
EXPLORE
The idea
Tracks
Prizes
Partners
TAKE PART
Rules
Find your kit
Submit
FAQ
ELSEWHERE
HF Org
Gradio
Hugging Face
X / Twitter
© 2026 Build Small · made small with love
≤ 32B params · open weights · run it yourself