QVAC (@qvac) header
QVAC (@qvac) profile picture

Infinite intelligence. Local. Any Hardware. Peer-to-Peer Hyper Swarm. No cloud. No compromise. QVAC is the decentralized AI platform for humans and machines.

Joined April 2025
Photo by QVAC (@qvac)Photo by QVAC (@qvac)Photo by QVAC (@qvac)Photo by QVAC (@qvac)Photo by QVAC (@qvac)Photo by QVAC (@qvac)Photo by QVAC (@qvac)Photo by QVAC (@qvac)Photo by QVAC (@qvac)Photo by QVAC (@qvac)
Tether's resources investment in local AI is massive, yet will continue to grow. @tether
Our engineering team just shipped an improvement that makes image generation on iPhone about 10x faster! In the video, an iPhone 17 in airplane mode makes a Stable Diffusion 2.1-base image in 6.8 seconds, then an SDXS image in 200 milliseconds. Everything runs on the phone.
20
9
3
86
14,067
Image generation on iPhone is solved. 77 images in 15 seconds on an old iPhone 13. Our latest improvement made image generation on-device 10x faster Only possible with QVAC.
Our engineering team just shipped an improvement that makes image generation on iPhone about 10x faster! In the video, an iPhone 17 in airplane mode makes a Stable Diffusion 2.1-base image in 6.8 seconds, then an SDXS image in 200 milliseconds. Everything runs on the phone.
6
14
1
72
215,368
Our engineering team just shipped an improvement that makes image generation on iPhone about 10x faster! In the video, an iPhone 17 in airplane mode makes a Stable Diffusion 2.1-base image in 6.8 seconds, then an SDXS image in 200 milliseconds. Everything runs on the phone.
30
140
7
3,438
2,600,308
The Neural Engine only runs models with fixed input sizes, so each model is exported for 512×512 images. The Stable Diffusion UNet is stored as a 6-bit palette, 622 MB instead of 1.6 GB, and both guidance passes of a step run in one call. Core ML now places 4,394 of its 4,399 operations on the Neural Engine.
1
8
809
An app built on it needs no server, so no one pays per image and it keeps working offline. The code is open source in our fork of stable-diffusion.cpp. Thanks to @StabilityAI for Stable Diffusion 2.1-base, IDKiro for SDXS and @madebyollin for the TAESD decoder.
8
753
Same with AI: when the data center goes down, every app built on it stops answering. That's why we built QVAC: so anyone has access to intelligence that runs on their own phone or laptop, with no single point of failure. By default, models download peer to peer over @Holepunch_to. QVAC. Unstoppable intelligence.
Internet has lost its way. Heavy centralization within 3/5 datacenter players created predictable point of failures and easy targets. @tether built unstoppable open-source peer-to-peer communication protocols that can resist to the worst disasters. Build on @Holepunch_to 🍐 Use @keet_io 🦜
1
4
1
26
1,487
Show this model a street photo and it finds where it was taken, in a tenth of a second, offline. It's MegaLoc by @gabriberton and Carlo Masone, new in QVAC SDK 0.24. In the video it compares each photo with 10,000 geotagged street photos and lands within 15 m every time.
2
2
2
26
2,140
MegaLoc works anywhere you can collect photos of known places. After indexing, search runs offline and your photo stays on the device. A robot that loses GPS can locate itself from streets it has photographed, and an app can tell you which street an old family photo shows.
1
2
263
The demo is open source (Apache 2.0) and MegaLoc is MIT licensed. You download the street photos once, with a free Mapillary token. Photos: Mapillary (CC BY-SA 4.0), Wikimedia Commons. Map: © OpenStreetMap contributors (ODbL). github.com/tetherto/qvac-exa…
2
222
Our new piece on @TechCrunch looks at the @Holepunch_to ecosystem and the comeback of peer-to-peer software. QVAC is part of it. Holepunch lets two devices talk directly, with no server in between. @keet_io uses it for messages, calls and file sharing. QVAC uses it to link your own devices into one private mesh, so a phone can hand heavier AI work to a stronger machine of yours. Read the article: techcrunch.com/sponsor/tethe…
3
4
2
26
1,847
QVAC SDK 0.24 is out, with vector search for RAG up to 8.2x faster and new image generation models. What's new: - TurboVec 1.1.2: RAG search in the SDK is now 2x to 8.2x faster, and more accurate - MegaLoc: a new model that recognizes places from a photo - Image generation: adds Flux 3 Klein, Qwen-Image-2.1 Turbo and MOSS-Image with layout control - qvac serve: better integration with tools such as Codex from @OpenAIDevs and @t3dotcodes - Sessions: one SDK runtime can now serve several apps at once, each with its own requests - Pocket TTS: now runs directly through the SDK, with streaming and cancellation - Cache sharing: conversations reuse each other's cache, so the start of a prompt they share is processed only once - AMD Ryzen AI NPU: Qwen3.5 can now use the NPU in recent AMD Ryzen AI chips, so your GPU stays free for another model - And several other developer experience improvements Learn more in the thread below. Complete release doc here: github.com/tetherto/qvac/rel… Star ⭐️ the repo to stay updated.
13
87
2
1,888
1,676,703
Transcription gained speaker attribution and more detail: - Whisper returns token timestamps and confidence, the detected language and speaker turns - Parakeet adds voice activity tuning, prewarming and device selection, with richer streaming results and lower streaming overhead - MOSS adds device selection, progress updates and detailed statistics
1
1
206
Other developer experience improvements: - calcTokens counts the tokens a string or a chat history with tools takes for the loaded model, without running inference - Fabric moves to llama.cpp b11739, which brings faster flash-attention prompt reading on Metal - Audio generation can run ACE-Step and its language model on separate devices, and returns output in chunks - GLM 5.3 Flash is available in the SDK and the AI SDK provider
208