







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
Introducing Julia 1 | Supersonic Labs
Julia 1 is our compact decision model. Explore the research, evaluation results, limitations, and model repository.

Supersonic Labs on Twitter / X
son... 🥀 https://t.co/bLoBkn6Vpo pic.twitter.com/bvBJG5wckx— Supersonic Labs (@supersonicai) September 24, 2026
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 (@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.

SupersonicLabs/Julia-1 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Supersonic Labs on Twitter / X
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
Thomas Yu on Twitter / X
Yesterday @supersonicai released an open weight jev-like model called julia-1This demo shows julia-1 running locally on my M5 Macbook Pro doing ~1500 tokens/sec calculating a live call's scam risk and risk types.Even for this moderately complex task, julia-1 was able to do… pic.twitter.com/VYHRvrjyIS— Thomas Yu (@thommyyu) September 27, 2026
Supersonic Labs | Intelligence, closer.
Independent research into useful, local artificial intelligence.


aviatesk/JETLS.jl
A new language server for Julia, enabling modern, compiler-powered tooling.
Why I no longer recommend Julia
For many years I used the Julia programming language for transforming, cleaning, analyzing, and visualizing data, doing statistics, and performing simulations.
Announcing Burn-LM (alpha): LLM Inference Engine
We're happy to announce the Burn-LM, an LLM inference engine based on Burn! The goal is to support any large model, LLM, VLM, and others, for inference but also for training (pre-training, post-training, and fine-tuning).

Why Numba and Cython are not substitutes for Julia - Stochastic Lifestyle
Sometimes people ask: why does Julia need to be a new language? What about Julia is truly different from tools like Cython and Numba? The purpose of this blog post is to describe how Julia’s design gives a very different package development experience than something like Cython, and how that can lead to many more optimizations. What I really want to show is: Julia’s compilation setup is built for specialization of labor which is required for scientific progress Composition of Julia codes can utilize the compilation process to build new programs which are greater than the sum of the parts I will also explain some of the engineering tradeoffs which were made to make this happen. There are many state-of-the-art scientific computing and data science packages in Julia and what I want to describe is how these are using the more “hardcore ... READ MORE
Julia vs Numba and Cython: Looking Beyond Microbenchmarks
We compare the performance of Julia and Numba, for a minimal benchmark that enables to see some fundamental difference between Julia and accelerated-Python.
Yet Another Jev Variant. I should create an acronym - YAJV! Julia 1: A decision model that runs on almost anything Blog: supersoniclabs.ia.br/julia-1/ Model: huggingface.co/SupersonicLabs/Julia-1
Introducing Julia 1 | Supersonic Labs
supersoniclabs.ia.br