Muninn TechnologyLocal AI, your hardware.

Run AI on your own hardware.

We develop local AI applications and services: open models quantized for everyday hardware, self-hosted AI agent tools, and mobile apps that connect to your own AI.

Explore our products

01

Model

More model. Less memory.

Quantization reduces the memory needed for model weights. Explore our FP8 and NVFP4 releases.

Explore open models

02

Agent

Put Hermes to work.

Run Hermes on your server. Choose the model provider it uses for conversations and file analysis.

See how Muninn connects

03

App

Take the connection with you.

Muninn connects your iPhone to the Hermes agent on your own server.

Meet Muninn

Our work

View products
Muninn app screen

No. 01

Muninn

Your iPhone, connected to the Hermes AI agent you run at home. A paired P2P connection puts your own server within reach.

Meet Muninn

No. 02

Quantized open models

Open models

We quantize open models into formats such as FP8 and NVFP4 so they can run on a single machine or GPU. Our models on Hugging Face have been downloaded more than 780,000 times.

As of November 2026.

Explore the models

Illustrative weight memory comparison

No. 03

BPSTracker

An iPhone app for tracking options credit spreads. See your open and closed positions and profit and loss at a glance.

Meet BPSTracker
BPSTracker app screen

A connection of your own

  1. 01iPhone
  2. 02Hermes
  3. 03AI provider

With Muninn, your messages go to your paired Hermes server. Hermes then uses the AI provider you configure, which may be a cloud service. We do not receive or store your conversation content. Read the Muninn privacy policy