Cloud AI has a speed limit it can never beat: the speed of light.
Every request to a cloud model is a round trip to a datacenter, and that round trip is bounded by physics. No provider can engineer it away.
Yes, a local model can be slower than a cloud API today. That gap is temporary. Hardware keeps getting faster and capable models keep getting smaller without losing quality.
But for anything that has to react in real time, a robot, a control loop, a live interface, the datacenter round trip is a hard floor. Local is the only option that stays reliable.
The cloud has a limit it cannot cross. The device in your hand does not.
That is why QVAC runs there.
Keet 4.17 is officially live.
🔍 Search Public Rooms: Find and join communities instantly from the search bar.
🛡️ Private Mode (Mobile): One toggle instantly hides all groups and messages from prying eyes.
📥 Unread Filter: Clean up the clutter and view your unread chats automatically.
No servers. No middleman. No data collected. Update now at Keet.io.
Profila retweeted
Keet knows nothing about you
You set your email to "Out of Office," but your chat apps didn't get the memo.
The moment you drop your bags, their central servers are already tracking your flight, your hotel, and the exact lounge chair you’re sitting on.
You took a holiday for pleasure, but the data collector came for business.
Leave big tech behind. Switch to Keet.io
QVAC SDK 0.11.0 is live. 🛠️
This release focuses entirely on unlocking next-generation local compute and advanced visual workflows.
What’s new:
Next-Gen Models: Core engine updated to the latest version of Fabric, unlocking full support for Qwen 3.5, Qwen 3.6, and Gemma 4.
Multi-GPU Support: The SDK can now split workloads across multiple graphics cards on the same machine, allowing you to run significantly larger models completely locally.
Multi-Image Conditioning: Blend multiple reference images together in a single generation for advanced style mixing and composition control.
On-Device Upscaling: Boost your generated images to high-quality resolutions, running securely on your own hardware.
More improvements are waiting under the hood. Check the change logs, update your SDK today, and start building with qvac.tether.io
Profila retweeted
No limits. No boundaries. No masters.
Remember the last time you sent a 30GB folder in a chat app?
You probably don’t, because most chat apps can’t handle it.
With Keet.io files travel directly from device to device. No Servers. No limits.
8 billion humans deserve an intelligence that doesn't blink when the signal dies. 🧠
Introducing @QVAC Psy, our foundational models built on the mathematical stability of Psychohistory.
With QVAC MedPsy, our local-first medical health AI model, we’ve proven that superior methodology beats raw parameter count. Our 1.7B & 4B models are delivering expert-level healthcare reasoning on consumer hardware.
The "tiny brain" for the next galaxy is here. Fully open-source. Fully sovereign.
Learn more
qvac.tether.io/models
If your AI needs a wire to work, it isn't yours.
QVAC is the local-first engine designed to run anywhere, even where the internet can't reach. Fully autonomous. Fully open source. Fully sovereign.
If you can dream it, you can build it. Even in another galaxy.
Start building the future of edge AI: docs.qvac.tether.io
Profila retweeted
Personal intelligence building blocks
If your AI needs a wire to work, it isn't yours.
QVAC is the local-first engine designed to run anywhere, even where the internet can't reach. Fully autonomous. Fully open source. Fully sovereign.
If you can dream it, you can build it. Even in another galaxy.
Start building the future of edge AI: docs.qvac.tether.io
Profila retweeted
QVAC Workbench just got a big feature bump
QVAC Workbench 0.6.0 is officially live. 🤖
This update marks a major shift toward a more natural, hands-free interface with several key features:
Conversation Mode: Enables full voice-to-voice interaction using automated transcription and text-to-speech (TTS), allowing the keyboard to be entirely optional.
Automated Model Selection: Streamlines the user experience by intelligently selecting the best local model for your device.
Snappier UI: Significant performance improvements to the interface for a faster and more responsive workspace.
Learn more: qvac.tether.io/products/work…
Profila retweeted
QVAC SDK and Fabric give people and companies the ability to execute inference and fine-tune powerful models on their own terms, on their own hardware, with full control of their data.
techcrunch.com/sponsor/tethe…
Profila retweeted
Privacy is normal.
No "normal person" ever needs to justify why they want privacy, or feel ashamed for wanting it.
Profila retweeted
For those that don't want to rely on the npm registry, Bare binary prebuilds are now available as GitHub release artifacts as well: github.com/holepunchto/bare-…
Simplicity is the ultimate sophistication.
That’s why Bare is small, modular, and now 1K ⭐ strong on @github
Check it out > github.com/holepunchto/bare
Profila retweeted
Return 1-0 has a developer meaning: Zero is the only success state. In our terms it means returning control to the individual by taking it away from surveillance capitalists. The only success state in Profila is You. You are ground zero. 1-0 is the journey back from being a product to being the starting point.
DM to invest in Zero. Final angel pre-seed round in April.
Profila retweeted
75% of executives say CX matters most — but most still build it on surveillance data. EY research shows zero-party data (declared intent) outperforms. One beauty brand got 35-50% of loyalty value from it. Declared beats inferred. ey.com/en_us/insights/consul… @ProfilaPrivacy
Profila retweeted
443 data breach notifications filed per day in 2025. Cookie consent violations are now the fastest-growing GDPR fine trigger. EUR 7.1B in cumulative fines and accelerating. securitywall.co/blog/gdpr-fi…



















