For the slower, explained version see Your first hour. On a GPU machine, read Install by hardware before step 1.
python3 -m venv nbx && source nbx/bin/activate
pip install neurobrix
neurobrix doctor
Expected: No blocking problem found. If not, see Troubleshooting.
neurobrix hub --category UPSCALER
neurobrix hub --search whisper
Expected: a table of models. The same list is at neurobrix.es/catalog. --category accepts any of the ten hub categories and the hub itself validates it: an unknown value prints the valid ones and exits with code 2.
neurobrix import caidas/swin2SR-classical-sr-x4-64
Expected: IMPORT COMPLETE.
importtakes the full slugorg/Model, case-sensitive.run,serveandupscaletake the bare name printed at the end of the import.
neurobrix upscale --model swin2SR-classical-sr-x4-64 --input photo.png --output photo-x4.png
Expected: photo-x4.png. Runs on CPU.
neurobrix import TinyLlama/TinyLlama-1.1B-Chat-v1.0
neurobrix serve --model TinyLlama-1.1B-Chat-v1.0
neurobrix chat
neurobrix stop
Expected: serve loads the model once into a background daemon; chat and run reuse it; stop frees the memory.
neurobrix run --model <Model> --prompt "A sunset over mountains"
Loads, runs, exits. While a daemon is running, a cold run of a different model is refused.
Your first hour · CLI reference
© 2025–2026 Hocine Benkelaya. NeuroBrix engine released under the Apache License 2.0.
Developed by Hocine Benkelaya · Supported and funded by Neural Network Holding Ltd · Commercial distribution by WizWorks OÜ