Secret AI: Mobile Offline Chat

📱 100% Offline & Secure Assistant on your phone
🤫 No Servers. No Logins. No Tracking. No Data Uploading.
🔴 TOP SECRET INTELLIGENCE

Try it today!👇

[Secret AI: Mobile Offline Chat @SecretAILabs]

Gemma 4 is now available on Secret AI — on Android, iOS, and macOS!

[Secret AI: Mobile Offline Chat @SecretAILabs]

Thinking Mode

[Secret AI: Mobile Offline Chat @SecretAILabs]

Gemma 4 is now available on Secret AI — on Android, iOS, and macOS!

[Secret AI: Mobile Offline Chat @SecretAILabs]

@googlegemma https://t.co/bX67KnbVcX

[Secret AI: Mobile Offline Chat @SecretAILabs]

Google just dropped Gemma 4 and it's not even close to fair. @googlegemma

Gemma-4-E2B-it, An edge-to-beyond model that runs on your phone and punches way above its weight. Multimodal, 140+ languages, beats models 20x its size. This thing is absurd for a local model.

We already support it in Secret AI. Load it up, no account needed, fully offline, and your data never leaves your device.

Why wait for corporate APIs when you can run it on your own hardware?

[Secret AI: Mobile Offline Chat @SecretAILabs]

LFM2.5-350M is out, and it’s actually pretty good. @liquidai

Tried it in Secret AI today and came away impressed. Fast (100+ tok/s), lightweight, and feels like a really nice fit for local use 🚀🚀🚀

[Secret AI: Mobile Offline Chat @SecretAILabs]

If roleplay isn’t your thing, here’s Qwen3.5-2B on iPhone in Assistant Mode.

You get the familiar chatbot experience, plus customizable features like chat backgrounds, avatars, and system prompts for a more personalized everyday conversation.

[Secret AI: Mobile Offline Chat @SecretAILabs]

Qwen 3.5 by @Alibaba_Qwen is wild — surprisingly strong for its size.

We tested it with our new feature "Characters" in Secret AI, and my iPhone turns into a private roleplay engine!

Here’s what Qwen3.5-2B looks like running on my phone. Fully local, fast, no cloud, no account. This is what on-device AI should feel like.

[Secret AI: Mobile Offline Chat @SecretAILabs]

@deepseek_ai You are the REAL Open AI

[Secret AI: Mobile Offline Chat @SecretAILabs]

The Right to Compute is the future. That’s exactly what we’re building at Secret AI — secure, private, and user-controlled AI.

[Abundance Institute @abundanceinst]

The "Right to Compute Act" guarantees that individuals and organizations can own and use computational resources — hardware, software, algorithms, even quantum systems — unless the government can show a compelling reason to restrict them. It pairs that freedom with sensible guardrails for critical infrastructure, requiring companies to follow national safety frameworks like NIST’s AI Risk Management Framework. @DispatchAlerts @taylordbarkley

[Secret AI: Mobile Offline Chat @SecretAILabs]

@linchi360 @liquidai Yeah, we’d love to provide an API — it’s actively in our dev roadmap, though we don’t have an exact release date yet.
Btw, is there any pain point with Ollama that’s stopping you from using it to achieve this? Would love to hear your thoughts

[Secret AI: Mobile Offline Chat @SecretAILabs]

It’s just a quick demo — extracting math formulas from images and analyzing them is still pretty heavy for a phone, and we can’t yet run the strongest models locally. But you’re right — we’ll try different models later to show what kinds of problems they can actually handle.

As for your question about internet access (sorry for missing your DM!), I’m not totally sure what you mean — are you asking if we could provide an API for it?

[Secret AI: Mobile Offline Chat @SecretAILabs]

Impressive work — multilingual retrieval is leveling up fast.

[Liquid AI @liquidai]

Meet our newest nano model: LFM2-ColBERT-350M ⚛️

At only 350M parameters, LFM2-ColBERT-350M allows you to store documents in one language and retrieve them in many languages with high accuracy and inference speeds of models a fraction of its size.

> Best cross-lingual retriever in the sub-500M class
> Outperforms larger models in German, Arabic, Korean, Spanish, Portuguese, Italian, French and Japanese
> Performs on par with much larger models in English
> Compact 350M design ready for large-scale and on-device retrieval
> Scales linearly with batch size, sustaining over 1K docs/sec in document encoding

1/n 🧵

[Secret AI: Mobile Offline Chat @SecretAILabs]

⚡ Pick your model like you'd pick your driver - match it to what you need. #SecretAI #PrivateAI #LocalAI

[Qwen @Alibaba_Qwen]

Big news: Introducing Qwen3-Max-Preview (Instruct) — our biggest model yet, with over 1 trillion parameters! 🚀

Now available via Qwen Chat & Alibaba Cloud API.

Benchmarks show it beats our previous best, Qwen3-235B-A22B-2507. Internal tests + early user feedback confirm: stronger performance, broader knowledge, better at conversations, agentic tasks & instruction following.

Scaling works — and the official release will surprise you even more. Stay tuned!

Qwen Chat: https://t.co/V7RmqMaVNZ
Alibaba Cloud API: https://t.co/zjCKdWee5v

[Secret AI: Mobile Offline Chat @SecretAILabs]

@Alibaba_Qwen Amazing QWEN

[Secret AI: Mobile Offline Chat @SecretAILabs]

@googleaidevs impressive

[Secret AI: Mobile Offline Chat @SecretAILabs]

@Zai_org congrats!

[Secret AI: Mobile Offline Chat @SecretAILabs]

Try Secret AI now!

[Secret AI: Mobile Offline Chat @SecretAILabs]

@ggerganov Totally agree! These models are making local AI so much better.
And big thanks to the llama.cpp community - you've made it possible to actually run these models on consumer hardware - even on the phone! This is amazing👏

[Secret AI: Mobile Offline Chat @SecretAILabs]

Try it now!
https://t.co/XnpyV2nCFh

[Secret AI: Mobile Offline Chat @SecretAILabs]

🔥 MiniCPM-V 4.5 is now LIVE on Secret AI!

Experience cutting-edge vision AI that processes images 100% offline on your device. No internet needed, no data tracking, complete privacy!

Huge thanks to @OpenBMB for this incredible breakthrough! 🙏