You were saying something...?yes, we classify responses 5x faster than Jev, using our own 144M-param model (Julia-1) on a 2021 i5 laptop while maintaining high accuracy. So no, we’re not like other open-source models. And fuck no, we’re not just a game neural network. https://t.co/xoz1HbRV2W pic.twitter.com/oiKZqVtqIC— Supersonic Labs (@supersonicai) September 24, 2026
Supersonic Labs on Twitter / X
Introducing Julia-1:Our first classification model that runs on almost anything.Learn more 👇https://t.co/YJCdEeIBSo pic.twitter.com/3cizsbG9ZB— Supersonic Labs (@supersonicai) September 26, 2026
SupersonicLabs/Julia-1 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
SupersonicLabs/Julia-1-ONNX · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Supersonic Labs on Twitter / X
lol, and we mogged Jev on a i5 ideapad with 16gb of RAM: https://t.co/T69NuUQxHK pic.twitter.com/VlPiH22xtb— Supersonic Labs (@supersonicai) September 23, 2026
Jalapeño’s first results show industry-leading speed and efficiency in AI inference
Jalapeño is a custom inference chip from OpenAI that delivers faster, more power-efficient AI inference, with higher throughput and lower latency for modern models.
Unfortunately, You Need to Know What the Jevons Paradox is
Unfortunately, You Need to Know What the Jevons Paradox is
High Performance AI Lab
High Performance AI Lab builds open inference systems and publishes the conditions behind every number — device, model, quant, and rep count.
AI Isn't as Powerful as We Think | Hannah Fry
Supersonic Labs (@supersonicai) on X
We're an AI research lab building fast, local, and accessible AI. Our mission is to make capable AI run on the hardware people already own.
Introducing Julia 1 | Supersonic Labs
Julia 1 is our compact decision model. Explore the research, evaluation results, limitations, and model repository.
Alex Cheema on Twitter / X
This is why we need open benchmarks for local AI.Otherwise it turns into tribalism and name calling.We will be publishing the largest database of open benchmarks for local AI, tested on 1,000+ real hardware setups. Every device, every interconnect, different… https://t.co/ZsU3PCdSsZ— Alex Cheema (@alexocheema) March 9, 2026
TurboQuant: Redefining AI efficiency with extreme compression
Amir Zandieh, Research Scientist, and Vahab Mirrokni, VP and Google Fellow, Google Research
Supersonic Labs | Intelligence, closer.
Independent research into useful, local artificial intelligence.
Georgi Gerganov on Twitter / X
gpt-oss is a great modelIMO OpenAI showed us the blueprint for winning local AI:- Interleaved SWA- Small head sizes in the attention- Attention sinks- Mixture of Experts FFN- 4-bit trainingAll of these parts combined together result in the best architecture suitable for…— Georgi Gerganov (@ggerganov) August 28, 2025