Claude Fable 5 Died in 90 Minutes. So I Rebuilt My Agent to Need No Frontier Model.

How I run a local AI agent on a Mac Mini. Open source Gemma, off grid on solar, the token bill at zero.

Claude Fable 5 was live for four days. Then it was gone in ninety minutes.

Anthrpic shuts Claude Fable 5 in 90 minutes, so local AI agents on Mac mini are becoming urgent for me.

The US government issued a directive, and Anthropic suspended access to Fable 5 and Mythos 5.

Claude Fable 5 was pulled as a result of a US Government Directive, source: Anthropic

Then everyone starts wondering: what if the model we're using right now gets banned by governments or companies?

Satya Nadella wrote about the deeper problem that week. His post passed three million views in hours.

A frontier without an ecosystem is not stable, as written in an article by Satya Nadella, CEO of Microsoft

His argument, stripped down, is that a company should be able to swap out a generalist model without losing what it built on top.

I read that as a warning.

So I rebuilt my agent to need no frontier model.

I build agents like this often. One works the night shift while I sleep.

Now I run a local AI agent on a Mac Mini, fully on my own hardware.

Let me show you how.

What we'll build: a local AI agent on a Mac Mini

A local AI agent on a Mac Mini, off-grid

An agent that needs no frontier model at all. (It does not even need a local grid.)

It runs on a box on my desk.

Mac Mini on my desk, running my Local

I talk to it from my phone.

My Local AI agent runs on my mac mini, talking through telegram.

It answers when the internet is down.

Five parts.

• A Mac Mini M4 with 16 GB.

• Ollama as the engine.

• An open model that fits the memory. (Gemma.)

• My agent, Hermes.

  • The one I used to copy millionaire trades with Claude Code.

• Telegram as the interface.

I even connected it to my EcoFlow. This Ecoflow can be charged through the Sun, so my system is full off grid when I am at home.

Ecoflow connected to my Mac mini

Results

Here is the open model against the frontier one, line by line.

If you do the math, the open model gets you most of the way.

The full Gemma 4 31B scores about 72 percent of Opus on the SWE-bench, the benchmark that matters for agents.

On easier work, chat, and summaries, it feels closer.

I run the smaller Gemma on my 16 GB.

Seventy percent of the frontier, and your token bill drops to zero overnight.

I have gone the free, local route before. Here is how to run Claude Code locally.

That trade is easy.

I think this is more than enough, because your bill will go to $0 all of a sudden.

Now let me show you how I built it, in three steps.