Tiiny Pocket

The First Pocket-Sized AI Supercomputer
The First Pocket-Sized AI Supercomputer
$2,099.00 USD
Sales tax excluded. Calculated at checkout based on your location.
Sales tax excluded. Calculated at checkout based on your location.

Product Features

  • 0 Token Cost

Run AI agents without monthly fees.

  • Portable but Powerful

142 × 80 × 22 mm, ready to run up to 120B-parameter models whenever you go.

  • Ready Out of the Box

Get models and agents running in just a few clicks—no complex setup, no learning curve.

  • Private by Architecture

Your data stays on-device, under your control, and becomes unreadable if the drive is removed.

  • Built for Continuous AI

Up to 3× greater energy efficiency, with a 30W TDP and whisper-quiet operation under 35 dB.

 

What's included
Color

Order Info:

  • Batch 1 ships to the contiguous U.S. only. Some remote addresses are excluded. Check our shipping policy for details.
  • For customers outside the U.S., to receive updates on availability in your region.
  • Limit one unit per customer. For bulk orders, contact us at business@tiiny.ai.

Free Shipping from U.S. Warehouse

Delivery in 7 business days.

Taxes and Fees

US orders: no import fees.

One-Year Warranty

One year of warranty protection.

Global Customer Support

Email us at support@tiiny.ai.

Payment Options

Payment method logos
  • Guinness World Record Holder
  • CES Official Exhibitor
  • Kickstarter $3.07M Pledged · 2k+ Backers
  • GitHub 9.8k Stars
Overview TiinyOS Specification Social Proof

Own Your Personal AI

Simply connect Tiiny AI Pocket to your laptop or PC to turn your device into a powerful local AI terminal. Built to run your AI agents with zero ongoing fees, zero friction, and complete privacy.

Run up to 120B in Your Pocket

Run up to

120B

in Your Pocket

0 Token Cost - Infinite Tokens

0 Token Cost

Infinite Tokens

Bank-Grade Security for Sensitive Work

Bank-Grade Security

for Sensitive Work

Zero-Config Open-Source LLMs and Agents

Zero-Config

Open-Source LLMs and Agents

30W Thermal Design Power

30W

Thermal Design Power

1TB PCIe 4.0 SSD

1TB

PCIe 4.0 SSD

30TOPS and 32GB on SoC, 160TOPS and 48GB on dNPU

30TOPS and 32GB

on SoC

160TOPS and 48GB

on dNPU

TiinyOS

Your AI Workflow Starts Here

A complete AI workspace for your most demanding tasks—from models and agents to automation—all in one place. Zero setup. Straight to work.

Model Store

Explore a wide range of models for reasoning, coding, creativity, and more.

Text Generation
gpt-oss-120b
gpt-oss-20b
Qwen3-8B
Qwen3-30B-A3B-Instruct-2507
Qwen3-30B-A3B-Thinking-2507
Qwen3-Coder-30B-A3B-Instruct
GLM-4.7-Flash
Qwen3-Coder-Next
Qwen3-Coder-30B-A3B-Instruct, etc.
Image-Text-to-Text
Qwen3.5-35B-A3B
Qwen3.6-35B-A3B
Qwen3.5-9B
Qwen3.6-27B
Qwen3.8-27B
Ornith-1.0-35B
Qwen3.6-35B-A3B-Turbo
gemma-4-26B-A4B-it, etc.
Text-to-Image
Z-Image-Turbo
ERNIE-Image-Turbo
FLUX.2-klein-4B
Z-Image-Turbo-Creating-Realistic
Z-Image-Turbo-Long-Prime-Lens
Z-Image-Turbo-CharacterDesignSheet
Z-Image-Turbo-Children-Drawing, etc.
Image-to-3D
Hunyuan3D-2.1, etc.
Image-to-Text
GLM-OCR
PP-OCRv6-Small
PP-OCRv6-Medium, etc.
Speech Recognition (ASR)
Qwen3-ASR-1.7B
Firered-ASR2-LLM
Fun-ASR-Nano-2512
Fun-ASR-MLT-Nano, etc.
Text-to-Speech (TTS)
Qwen3-TTS-12Hz-1.7B-Base
Qwen3-TTS-12Hz-1.7B-CustomVoice
Qwen3-TTS-12Hz-1.7B-VoiceDesign
supertonic-3, etc.
Music Generation
Foundation-1
SongGeneration-v2-large
Text Embedding
Qwen3-Embedding-0.6B, etc.
Text Reranking
Qwen3-Reranker-0.6B, etc.

Agent Store

Ready-to-Use Agents for real tasks. Or bring your own.

Assistants
HermesAgent, OpenClaw, AutoGPT, Open WebUI, etc.
Coding
KiloCode, opencode, etc.
Workflow
n8n, Dify, etc.
Office
Tiiny Meeting, etc.
Entertainment
SillyTavern, etc.

3 Ways to Work with TiinyOS

Chat

Chat Icon

Private AI Chat

Ask questions, analyze files, and get instant answers with your local AI models.

Search

Search Icon

Real-Time AI Search

Connect to the web for up-to-date information, and fact-check result, with all processing on your own device.

Task

Task Icon

AI Agents and Automation

Describe your goal, and Tiiny coordinates AI agents to automate workflows from planning to execution.

Full Technical
Specifications

SoC
CPU (arm v9.2) + NPU
30 INT8 TOPS
dNPU
160 INT8 TOPS
Memory
80GB LPDDR5X @6400MT/s
(32GB on Soc, 48GB on dNPU)
Storage
1TB PCIe 4.0 SSD
Audio
Internal mono audio output
Microphone
Built-in digital microphone
Bluetooth
BT 5.3 w/LE
Wi-Fi
802.11a/b/g/n/ac/ax(Wi-Fi max transfer speed: 2.4 Gbps)
Interfaces
Type-C × 3
Power
TDP 30W (65W adapter required)
Weight
300g
Dimensions
142 × 80 × 22 mm
Compatible System
Windows 11 and later, macOS 15 and later

Why People Love Tiiny Pocket

dropped my claude sub and Tiiny and OpenCode handle all code work now. Been a very happy camper - it just cranks out tokens
mrwizx
Coding with OpenCode
Yeah, I kinda wish I'd sprung for a second one when I backed the campaign.... man if I knew then what I know now, the temptation would have been absolutely real
Been using mine a lot at work lately, oddly enough not for coding, but for running Hermes in the background doing component/dev board research for me while I do actual work
...
Works nicely, spend a small amount of money for the planning/reasoning phase of a task and then let the Tiiny act like a token factory doing the grunt work "for free".
helldiving_firehawk
Background research with Hermes
I just thought I wanted to tell you how insanely impressive Tiiny Music is.
Over the weekend I created a fake band, a fake album and even used tiiny to create the album art and then had tiiny music create the tracks. Once I formulated the prompt each track took about 5 minutes to complete.
A few tracks went off the rails but thankfully I could stop it. Great job!
RubyTheJeep
A virtual band, album art, and music
I've also experimented with having a hosted/paid model like Kimi-K3 or Qwen3.8 Flash handle planning and then delegate things to a model on my Tiiny. Works nicely, spend a small amount of money for the planning/reasoning phase of a task and then let the Tiiny act like a token factory doing the grunt work "for free".
helldiving_firehawk
Background research with Hermes
I loaded qwen-3.8-27b and gave it the GM core rulebook and toolkit documents for the new Discworld RPG, told it to GM a new game.
It did a really amazing job. There were several laughs and the scenes were believable. The die rolls were consequential, but also funny. This model did a fantastic job and we will for sure run this again.
DNSGeek
Bringing a tabletop game to life
I consult with technology companies. Many of my clients need me to respect their IP, and I can't work with thier content on public infrastructure.
I've had to carefully divide my work so that much of it can be done on public cloud inference, and specific bits could be assembled and completed using models that would run on my 24Gb Mac Mini M4 Pro. I use OffGrid and a Gemma 4 12B to take notes in meetings, for example.
But this is a game changer for me. I can actually research, draft content and format finshed work product using a 30B class model. And now my meeting notes taker can run on a 30B class model.
AntAttack
Research and writing with a 30B model
i used openclaw jan-march, hermes march-sept, i just tried using openclaw with the tiiny again... big "wtf?"... i'm now setting hermes up with the tiiny
i moved my daily briefing pipeline over to use tiiny yesterday (news sources -> llm w/persona prompting filtering, summarizing, selection stories -> obsidian vault)...
gotta say, I love the tiiny... low 10s tk/s is enough while its running almost silently... i had an L40s running qwen3.8 at like 35tk/s for the last 2 months and had to wear noise canceling headphones in my own office the entire time now that ive got tiiny i've got my office back, the tk/s difference is 100% worth it because its SILENT and i can BRING IT WITH ME when I travel lol
Sdrawkcab
Quiet enough for my office. Portable enough for travel.
Blam. It triggers when I leave, when i get home. It will remind me "since youre leaving home, remember you needed an oil filter #kn256 etc" Things like that
If it doesnt know or understand, it opens a line to tiiny in tailscale and openuiwebportal and tiiny figures it out
It sets up a grammar for correct actions and answers, and done.
I made it a rules and logic based systm, that runs mostly on my Kamrui mini PC, written by tiiny in JS
It tracks, learns, and now im setting up a low latency 100% local project i can load onto an SD card and can run on any pc. Dude... Zero token limits is just.... wow....
DoctorNurse89
A shared AI setup for the household
The Expert Take
The Expert Take
Product Expert Video 1
Product Expert Video 2
Product Expert Video 3
Product Expert Video 4

Inspired by the Community

Real workflows shared by people using Tiiny AI Pocket.

Cost Saving

"Sounds like we are all doing almost the same thing, for starters coding assistant that doesn't cost an arm, will also like in to home automation and knowledge base optimisations"

@ Alister Galpin
Local and Offline

"I plan on immediately assigning it to a part of my stack of two Mac Studios, a Mac Mini, and a Mac Laptop and UGREEN NAS, and take a local LLM to run several tasks. Very excited for it's role in my ever growing stack!"

@ John Harrington
Privacy

"Move to a local model for most of my prototyping. Move parts of a LLM knowledgebase to private as well. I love the local and private aspect, coupled with the mobile form factor."

@ OpenShortestPathFirst
Developer

"I want to experiment with building an always on software dark factory. I'd never want to spend the money an API to experiment with it, so this seems like a low-cost/low-risk way to."

@ Jeremy
Assistant

"Upload my technical library and notes and have it function as an assistant in my professional and entrepreneurial endeavors."

@ Troy Sanders
Portability

"portable brain shard for my distributed personal assistant. that power bank wouldn't hurt."

@ Hunter Morgan
The Global Headline
The Global Headline
"LLMs usable with this machine are said to be perfect for "PhD-level reasoning, multi-step analysis, and deep contextual understanding.""
"Operating in the "golden zone" for personal AI, it handles most real-world tasks and scales up to 120B parameters, delivering GPT-4o-level intelligence."
"Tiiny AI has managed to pack in a whopping 80GB of RAM and 1TB of SSD storage into this miniature device in order for it to actually be able to handle intensive AI processing."
"For the first time in AI supercomputing, a pocket-sized device is capable of running up-to a full 120-billion-parameter large language model entirely on-device."
"The device is a mini PC designed to execute advanced inference workloads without cloud access, external servers, or discrete accelerators."
"It is as small as a power bank, offering performance typically associated with much larger and more expensive hardware."

FAQ

Why can't I place an order?
This batch is available to order only with an eligible shipping address in the contiguous U.S. We're working to open orders in more regions as soon as possible. Sign up for email updates to find out when and where orders open next.
Where do you ship, and how long does it take?
For U.S. orders, we ship directly from our U.S. warehouse. Delivery is estimated to take 7 business days after we process your order. We'll email you the tracking details as soon as they're available. For complete shipping details, please see our Shipping Policy.
What payment methods do you accept?
We accept major credit and debit cards, including Visa, Mastercard, and American Express, as well as supported digital wallets such as Apple Pay and Google Pay. Available payment methods may vary by country and will be shown at checkout.
Installment payments are not currently available.
What is included in the box?
Tiiny Pocket comes with everything you need to get started:
  • Tiiny Pocket
  • Soft carrying pouch
  • Cable pouch
  • 65W power adapter and power cable
  • USB-C data cable
  • Quick Start / User Manual card
Is there a subscription or monthly fee?
No. Tiiny Pocket is a one-time hardware purchase. Running supported models locally on Tiiny Pocket does not require a subscription or per-token fee.
What is Tiiny's return policy?
Return eligibility depends on your purchase location and applicable consumer laws. Please see our Return and Refund Policy for the terms that apply to your order.
Tiiny does not currently offer an additional voluntary 30-day return program beyond any return rights required by applicable law.
If your Tiiny Pocket arrives damaged, defective, or incorrect, please contact support@tiiny.ai. We'll help arrange repair, replacement, or another appropriate resolution in accordance with our warranty and applicable law.
What does the warranty cover?
Tiiny Pocket includes a 1-year limited hardware warranty starting from the date of delivery. It covers manufacturing defects and hardware failures that occur under normal use.
The warranty does not cover accidental or physical damage, misuse, unauthorized modifications that cause the issue, or normal cosmetic wear.
If you need help, contact support@tiiny.ai and our team will assist with diagnosis, repair, or replacement where applicable.