# Reson8's Rumble-2-Flash Puts ASR in 0.5B Params

> A compact open speech recognition model aims to transcribe more than 40 languages without heavyweight infrastructure.

Published by The Open Weights on Nov 18, 2026. Canonical: https://theopenweights.com/news/rumble-2-flash-twup

## Key facts

- Company: Reson8
- Model: Rumble-2-Flash
- Version: 2-Flash
- Category: Speech → Text
- Modalities: Speech → Text
- License: Other (Open weights, commercial use allowed)
- Parameters: 500M
- Architecture: Qwen3ASRForConditionalGeneration
- Precision: BF16
- Weights size: 1 GB
- Languages: 40+ languages
- Significance: notable
- Published: 2026-11-18
- Last verified: 2026-11-20
- Hugging Face: https://huggingface.co/Reson8/Rumble-2-Flash
- Canonical URL: https://theopenweights.com/news/rumble-2-flash-twup

Reson8 has released **Rumble-2-Flash**, an open speech-to-text model that packs multilingual automatic speech recognition into roughly 500 million parameters. According to the company's [announcement on Hugging Face](https://huggingface.co/blog/rumble-2-flash), the model handles transcription across more than 40 languages.

The headline here is size. At 0.5B parameters, Rumble-2-Flash sits well below the billion-parameter threshold, which makes it a candidate for deployment on modest hardware, edge devices, or latency-sensitive pipelines where larger ASR systems are impractical.

## Why it matters

Multilingual speech recognition has historically demanded significant compute, and the strongest systems have often been closed or expensive to run. A small, openly available model that spans dozens of languages lowers the barrier for developers building:

- Offline or on-device transcription
- Voice interfaces for underserved languages
- Cost-constrained batch processing at scale

The model is published under a non-standard license, so teams should review the terms before building on it commercially. As the first entry in the Rumble-2 line, it establishes a baseline worth watching as Reson8 iterates on coverage and accuracy.

## Get the model

- [Hugging Face](https://huggingface.co/Reson8/Rumble-2-Flash)
- [Announcement](https://huggingface.co/blog/rumble-2-flash)

## Sources

- [Rumble-2-Flash: an open 0.5B speech model for 40+ languages](https://huggingface.co/blog/rumble-2-flash) — Announcement, Nov 18, 2026
- [Reson8/Rumble-2-Flash](https://huggingface.co/Reson8/Rumble-2-Flash) — Hugging Face, Oct 14, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Reson8's Rumble-2-Flash Puts ASR in 0.5B Params", The Open Weights, Nov 18, 2026, https://theopenweights.com/news/rumble-2-flash-twup