Supersonic Labs Releases Julia 1: A 144.3M-Parameter Open Decision Model That Runs on a CPU
Supersonic Labs released Julia 1, a 144.3M-parameter Apache 2.0 decision model that picks among supplied answers on CPU.
Supersonic Labs, a small Brazilian AI lab, released Julia 1, an open 144.3 million-parameter decision model under Apache 2.0. It takes context, a question, and 2 to 20 candidate answers and returns a choice plus softmax probabilities; it does not generate text. The model keeps JHU CLSP’s mmBERT-small encoder and a decision head; the lab says training and experiments cost about US$104. Pilots beat TypeSafe Jev references on several tasks but scored 64/100 on 72-label Banking77 versus an 87% reference, with a 33.15 ms median per decision on an Apple M4.
- 144.3M parameters, Apache 2.0 weights, CPU and ONNX/WebGPU builds
- Choice, ordered score, and yes/no decisions over 2–20 options
- Built on mmBERT-small; not a fine-tuned Qwen model
- Trails Jev on Banking77 (64 vs 87) despite wins on smaller pilots
- Cloud GPU training spend about US$104; hosted API not open yet
- Vendors
- Supersonic Labs
- Products
- Julia 1
- Countries
- Brazil
- AI models
- Julia 1mmBERT-smallJevGLiNER2.5
From the original article
4 min read at marktechpost.com
Supersonic Labs has released Julia 1, a 144. 3M-parameter decision model built on mmBERT-small. It takes context, a question, and 2 to 20 options, then returns one choice with probabilities.
By Michal Sutter · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.