# Nimbus model sizes and sources

> Nimbus is Crele's model for live audio, with about 97M audio parameters and a 0.6B text encoder. It answers yes/no questions every 40 ms.

Updated 2026-11-04 (Australia/Adelaide)

By Crele · Hugging Face weights upload: 2026-10-30 · OPEN

A decision model for live audio. You ask yes/no questions in plain English (is music playing? is someone speaking?) and it answers every 40 ms of a stream with yes, no or can't tell, real time on a laptop CPU. The date is when the weights went up on Hugging Face.

## Facts

- Size: About 97M parameters on the audio, plus a 0.6B text encoder (Qwen3-Embedding-0.6B) that reads each question once
- Licence: Apache-2.0, code and weights
- Inputs: A live audio stream plus yes/no questions; answers yes, no or cant\_tell per 40 ms

## Claims and sources

- **VENDOR-REPORTED**: Says yes a median 0.24 s after a sound starts over the sounds it caught on 500 real AudioSet clips (speech 0.21 s, 97% of 181 speech onsets caught); reworded questions it never trained on scored 0.892 mean AUROC against 0.911 on its own wording [source](<https://github.com/Crele-AI/nimbus>)

## Links

- [Source: GitHub](<https://github.com/Crele-AI/nimbus>)
- [Source: Hugging Face](<https://huggingface.co/crele/nimbus-v1>)

## Related projects

No related projects are listed in the registry.