
Enigmus 1.0 is now on the Mac App Store, alongside the iPhone and iPad build. The architecture is identical: language models run locally, and the prompt, the generated tokens, and the chat history stay on the machine. There is no account and no backend. Network access happens only while a model is being downloaded; inference itself runs with the machine offline.

Inference uses Apple's [MLX](https://github.com/ml-explore/mlx) framework, which runs the model on the Apple silicon GPU through Metal against the unified memory pool shared with the CPU. The models are 4-bit quantized builds of the open-weight Qwen3 family. A Mac's larger unified memory raises the ceiling on both model size and context length compared to a phone. A small model is bundled in the app, so the first message works before any download. The sections below cover what the Mac build does, one screen at a time.

## Local by default

The onboarding screen documents the runtime model up front rather than in a settings pane: conversations are stored on-device, there are no accounts, servers, or telemetry, and the weights are publicly released rather than a proprietary endpoint. These are properties of the design, not switches — with no outbound traffic during inference, there is no server-side log or profile to produce.

<img src="/images/launch-mac-welcome.webp" alt="Enigmus welcome window on macOS listing three principles: private, local only, open weights" style={{maxWidth: '720px', width: '100%', display: 'block', margin: '0 auto', borderRadius: '8px'}} />

## A desktop window, with history in the sidebar

On macOS the app is a standard window. Conversation history is held in a local SwiftData store and listed in a searchable sidebar; the active conversation fills the main pane, with keyboard and pointer input. Generation streams token by token from the local model, so throughput is bounded by the GPU rather than a network round-trip, and it proceeds with networking disabled. Output is rendered as markdown — headings, lists, and syntax-highlighted code blocks — and LaTeX is typeset rather than left as source; the screenshot below shows the model deriving Euler's formula with both inline and display equations. Reasoning-tuned models (Qwen3 4B and larger) emit a separate thinking trace, shown in a collapsible block ahead of the final answer.

<img src="/images/launch-mac-chat.webp" alt="Enigmus on macOS showing a conversation-history sidebar and a chat rendering Euler's formula with typeset equations" style={{maxWidth: '720px', width: '100%', display: 'block', margin: '0 auto', borderRadius: '8px'}} />

## Memory governs model selection

Both feasibility and throughput are bounded by memory, so the installer is built around the machine's limits. It reads the available RAM and free storage, lists each model with its on-disk size, marks the largest build that fits the memory budget as recommended, and disables the ones that exceed available RAM or storage. In the screenshot, a 24 GB machine is pointed at an 8B 4-bit build and a 14B build is disabled for insufficient free storage. The catalog spans the bundled model through larger Qwen3 variants, including reasoning-tuned builds. Weights are fetched from Hugging Face's CDN, the only optional network request in the app.

<img src="/images/launch-mac-models.webp" alt="Model installer on macOS showing available RAM and free storage, a list of Qwen3 models with sizes, a recommendation, and a disabled model" style={{maxWidth: '720px', width: '100%', display: 'block', margin: '0 auto', borderRadius: '8px'}} />

## Getting it

The Mac build targets Apple silicon (M1 or newer) and runs the same inference engine as the iPhone and iPad release. It is free, with no account.

[Download Enigmus on the Mac App Store](https://apps.apple.com/us/app/enigmus/id6771532268?platform=mac)


Enigmus 1.0 on the Mac: local LLMs on Apple silicon


Enigmus 1.0 is out on the App Store for iPhone and iPad. It runs large language models entirely on the device — the prompt, the generated tokens, and the chat history never leave the hardware. There is no account to create and no server to talk to. The only time the app touches the network is when a new model is downloaded; after that, it works in airplane mode.

Inference runs on Apple's [MLX](https://github.com/ml-explore/mlx) framework, which executes on the Apple silicon GPU and the unified memory shared with the CPU. The models are 4-bit quantized builds of the open-weight Qwen3 family, which keeps memory use low enough that a phone can hold a useful model resident and still leave room for the rest of the system. A small model ships inside the app, so there is something to talk to within seconds of the first launch — no download gate before the first message. The sections below walk through what 1.0 actually does, one screen at a time.

## Local by default

The first launch states the constraints up front rather than burying them in a settings screen: conversations stay on the device, there are no accounts or servers or telemetry, and the models are publicly released open weights rather than a proprietary endpoint. These aren't toggles that can be switched off later — they're a consequence of the architecture. With nothing leaving the device, there is no log to leak and no profile to build.

<img src="/images/launch-privacy.webp" alt="Enigmus onboarding screen listing three principles: private, local only, open weights" style={{maxWidth: '300px', width: '100%', display: 'block', margin: '0 auto'}} />

## A chat that works with the radios off

The chat itself is a normal multi-turn conversation — ask a question, follow up, change direction — except that each reply is generated locally and streams in token by token as the model produces it. Because nothing is round-tripping to a data center, the latency is whatever the device's GPU can manage, and it keeps working with Wi-Fi and cellular fully disabled. Past conversations are kept in a local SwiftData store, so history persists between sessions without ever being synced anywhere.

<img src="/images/launch-chat.webp" alt="A multi-turn chat in Enigmus continuing a short story" style={{maxWidth: '300px', width: '100%', display: 'block', margin: '0 auto'}} />

## Picking a model the device can actually run

On-device inference lives or dies by memory, so the model installer is built around it. It reads the available RAM and pairs each model in the list with its on-disk size, marks the largest one that comfortably fits as recommended, and greys out the ones that would not — a 30B model is simply unavailable on a phone that can't hold it. The catalog ranges from the tiny bundled model up through larger Qwen3 variants pulled from Hugging Face, including reasoning-tuned builds. Downloads come from Hugging Face's public CDN, the one piece of optional network traffic in the app.

<img src="/images/launch-models.webp" alt="Model installer showing available RAM and a list of Qwen3 models with sizes and a recommendation" style={{maxWidth: '300px', width: '100%', display: 'block', margin: '0 auto'}} />

## Measuring before committing

Different models trade quality for speed and memory in ways that depend on the specific device, so 1.0 includes a benchmark that runs a model and reports the numbers that matter: load time, the memory the model occupies versus what the system has, and throughput split into prompt processing and generation-only tokens per second. It's a quick way to find out whether a given model is fast enough to be pleasant on a particular iPhone or iPad before settling on it for daily use.

<img src="/images/launch-benchmark.webp" alt="Benchmark results showing load time, model memory, total memory, and tokens per second" style={{maxWidth: '300px', width: '100%', display: 'block', margin: '0 auto'}} />

## Markdown, code, and real math

Replies render as formatted markdown rather than a wall of plain text — headings, lists, and syntax-highlighted code blocks — and LaTeX is typeset properly instead of being left as raw `\(` source. The screenshot below is the model working through Euler's formula, with both inline expressions and display equations laid out as actual math. Reasoning-capable models (Qwen3 4B and up) also show their thinking in a collapsible section before the final answer, which makes it easier to see how a conclusion was reached.

<img src="/images/launch-math.webp" alt="Enigmus rendering Euler's formula with typeset inline and display equations" style={{maxWidth: '300px', width: '100%', display: 'block', margin: '0 auto'}} />

## Dark mode and bigger screens

Enigmus follows the system appearance, so the same conversation reflows into a dark theme without any fiddling. The layout also adapts beyond the phone: on iPad and Mac it spreads into a wider arrangement with keyboard and pointer support, and a handful of cosmetic settings — tint color, fonts, and haptics — are there for anyone who wants to adjust them.

<img src="/images/launch-dark-mode.webp" alt="The same Enigmus chat shown in dark mode" style={{maxWidth: '300px', width: '100%', display: 'block', margin: '0 auto'}} />

## Getting it

Enigmus 1.0 requires an iPhone 13 or newer (A15 Bionic or later) or an iPad with an M1 chip or newer. The Mac build is close behind. It's free, with no account.

[Download Enigmus on the App Store](https://apps.apple.com/us/app/enigmus/id6771532268)


Enigmus 1.0: local LLMs on iPhone and iPad


As AI becomes deeply integrated into daily life, a critical question emerges: what happens to all the data these systems consume? From voice assistants to recommendation algorithms, modern AI is built on vast amounts of personal information. Understanding the privacy implications isn't optional anymore—it's essential.

## Why Privacy Matters

Privacy in AI isn't just about keeping secrets. It's about maintaining control over digital identity. AI systems process everything from browsing patterns to biometric data, creating detailed profiles that reveal far more than any single data point would suggest.

The scale is staggering. A typical large language model trains on hundreds of billions of data points. Interactions with cloud-based AI services often become part of that training data—whether users realize it or not.

### The Real Risks

**Data Exposure**: Centralized AI services create attractive targets. A single breach can expose millions of conversations, queries, and personal details simultaneously.

**Inference Attacks**: Even anonymized data can be de-anonymized. AI itself can reconstruct personal information from seemingly harmless metadata.

**Model Memorization**: Large language models can inadvertently memorize and reproduce sensitive information from their training data, including private conversations and personal details.

**Behavioral Profiling**: Continuous interaction with AI services generates behavioral patterns that can predict decisions, preferences, and vulnerabilities.

## The Local Alternative

The architecture of AI deployment matters enormously for privacy. When AI runs locally on a device:

- Data never leaves the hardware
- No server logs capture queries
- No third party can access conversations
- Users maintain complete control over what the model sees

This isn't about having something to hide. It's about the principle that thoughts, questions, and creative explorations belong to the individual.

## Privacy-First AI

AI capability and strong privacy aren't mutually exclusive. On-device processing through frameworks like Apple's MLX demonstrates that language models can run entirely locally, respecting the boundary between private digital life and external servers.

The future of AI should enhance human capability without compromising human autonomy.


Showing posts fromprivacy

Enigmus 1.0: local LLMs on iPhone and iPad

Enigmus 1.0 on the Mac: local LLMs on Apple silicon

Why Privacy in AI Matters More Than Ever