How To Setup Hermes With Ollama (One-Click, Free)

How to setup Hermes with Ollama is the question I get asked most this month — and the answer is way easier than you think.

Most people think setting up Hermes is technical.

GitHub repos.

Terminal commands.

Configuration files.

It's not.

The whole thing takes about 20 seconds with a one-click setup.

This post shows you exactly how.

Why Hermes With Ollama

Hermes on its own is one of the best AI agents I've used.

Ollama makes it free.

Together you get a fully working AI agent running on your own computer with no per-token costs.

Three reasons this matters:

No bills. Cloud models charge per token. Local models don't.
Privacy. Your data never leaves your machine.
Always on. No API outages, no rate limits, no internet required after install.

If you've been paying API bills, this is the upgrade.

The Three Ways To Setup Hermes

There are three real options.

I'll show you all three so you can pick what suits you.

Option 1 — Cloud model (free, instant)

Quickest way to try Hermes if you don't want to install much.

Free cloud models work great with Hermes — but they have token limits.

Good for testing.

Not great for heavy daily use.

Option 2 — Local model with Ollama (free, slightly slower setup)

The recommended path for most people.

Free, no token limits, runs on your computer.

This is the focus of this post.

Option 3 — Max Hermes (hosted, paid)

A non-technical option hosted in the cloud.

You don't get the customisation of the terminal version, but you don't have to install anything.

Paid.

OK for someone who wants zero friction.

The Quick Path: Hermes + Ollama In 5 Steps

Here's the exact one-click setup.

Step 1 — Download Ollama

Go to ollama.com.

Download for your OS.

Install like a normal app.

That's the prerequisite.

Step 2 — Pick a model

On the Ollama models page, browse what's available.

Recommended for Hermes:

DeepSeek — designed for agentic tasks, lightweight.
Gemma 4 — small, efficient, only ~7GB.
Qwen 3.6 — solid agent-friendly model.
Nemotron 3 Nano Omni — Nvidia's new agentic model, great for sub-agents.

If you're not sure, start with DeepSeek.

Step 3 — Run the install command

Each model has a single command on its Ollama page.

Copy it.

Paste into your terminal.

Hit enter.

Wait for the model to download.

Step 4 — Connect Hermes

Hermes will auto-detect Ollama once it's running locally.

If it doesn't, point Hermes at your local Ollama URL — usually http://localhost:11434.

Step 5 — Run the agent

Open Hermes.

Pick the Ollama model from the provider dropdown.

Send a message.

Done — you're now running Hermes with a free local model.

🔥 Want my full Hermes + Ollama setup? Inside the AI Profit Boardroom, I share my exact Hermes config, model recommendations per use case, system prompts, and a 2-hour Hermes course covering every workflow. Plus weekly screen-share coaching where you can ask anything live. 2,800+ members. → Get the full setup

Cloud Vs Local: When To Use Each

I run both depending on the task.

Use cloud models when:

You need maximum reasoning power.
Token limits aren't an issue.
You're working with very long context.

Use local Ollama models when:

You want zero token costs.
You care about privacy.
You're running the agent 24/7.

For most daily Hermes work, local Ollama is the smart pick.

The Best Models To Use

Quick recommendations.

Best free local for most users: Gemma 4 (only 7GB).

Best agentic local model: DeepSeek (designed for agent tasks).

Best for sub-agents: Nemotron 3 Nano Omni (Nvidia's new release).

Best for coding: Qwen 3.6.

For cloud models on Hermes, the recommended combos are:

Kimi K2.5
GLM 5.1 Cloud
Qwen 3.5 Cloud
Minimax M2.7 Cloud

I cover deeper model comparisons in Hermes Gemma 4 and Hermes DeepSeek.

What You Can Do With Hermes Once It's Running

Hermes works with 70+ skills out of the box.

Some I use daily:

Web search.
Browser automation.
Code generation.
Memory profiles.
Text-to-speech.

All free, all local, all running on Ollama.

For full skill walkthroughs, see Hermes Agent Workspace.

If You're Not Technical

There's a shortcut.

Don't fight the terminal.

Use Claude Code or Codex to do the install for you.

Here's the trick:

Copy the Ollama install command for the model you want.
Paste it into Claude Code.
Type "set this up for me".

Claude Code (or Codex) will run the install and configure Hermes for you.

Zero friction.

I cover this trick in Free Claude Code too.

Common Setup Issues

Three things people hit:

1. Ollama not running.

Make sure Ollama is open before you start Hermes.

It needs to be running in the background.

2. Model not found.

Run ollama list in terminal to confirm the model is downloaded.

If not, run the install command again.

3. Hermes can't see the model.

Restart Hermes after Ollama starts.

It'll pick the model up on launch.

Why Local Beats Cloud Most Of The Time

I'll be straight.

If you're just experimenting, cloud is fine.

If you're running an agent for real work — content, SEO, automation — local Ollama saves you a fortune.

I've shifted 80% of my Hermes work to local Ollama models.

API bills dropped to nearly zero.

Performance is more than enough for daily tasks.

Quick Recap

To setup Hermes with Ollama:

Download Ollama from ollama.com.
Pick a model (DeepSeek or Gemma 4 are great starters).
Run the install command in your terminal.
Open Hermes.
Select your Ollama model.
Send a message.

That's it.

🚀 Want all my Hermes automations + 70+ skills configured? The AI Profit Boardroom has the full Hermes course (2 hours), my exact skill stack, and weekly live coaching. Daily training drops, and a community where 2,800+ members share their setups. → Join here

FAQ — How To Setup Hermes With Ollama

Do I need a powerful computer?

Gemma 4 (7GB) runs on most modern laptops.

Bigger models like Nemotron 3 (28GB) need more RAM.

Is Hermes with Ollama actually free?

Yes — both Hermes and Ollama are free, and local models cost zero per token.

How long does the install take?

The Ollama install is quick.

Model download depends on size — 5–20 minutes for a typical model.

Can I switch between models on Hermes?

Yes — you can swap models any time without restarting Hermes.

Will it work without internet after setup?

Yes — once the model is downloaded, you can run Hermes fully offline.

Which model should a beginner pick?

Start with Gemma 4 if your laptop is light, or DeepSeek if you've got more RAM.

Can I use cloud and local models on the same Hermes setup?

Yes — Hermes supports multiple providers at once.