FireRedVAD-Stream-VAD needs about 0.5 GB of memory at its main file (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.0 GB to 0.0 GB.
FireRedVAD – lightweight voice activity detection in 100+ languages
FireRedVAD is a DFSMN‑based model for voice activity detection and audio event detection. It is released as a GGUF conversion of the original FireRedTeam/FireRedVAD. The model is small, with about 588K parameters and a 2.4 MB file size.
Good at
- High‑accuracy VAD on 100+ languages
- Streaming and non‑streaming modes
- Audio event detection in speech, singing, and music
Limits
- No vision support
- No quantization variants listed
- Requires 16kHz 16‑bit mono PCM audio
Best for
- Real‑time VAD in embedded devices
- Batch audio processing for transcription pipelines
- Audio event tagging in multilingual datasets
Who it’s for. Developers building voice‑enabled applications that need accurate speech detection across many languages. Researchers testing VAD models on multilingual benchmarks. Engineers deploying lightweight models on edge hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.0 GB | 0.5 GB | Fits | Get file → |
All provided GGUF files are unquantized F32 and have a file size of 0 GB with an estimated memory usage of 0.5 GB at 8 k context. For systems with 1 GB VRAM, the unquantized model fits comfortably. If memory is tighter, no quantized variants are available in the list, so the unquantized model is the only option.
What GPU do you need for FireRedVAD-Stream-VAD?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
Which FireRedVAD-Stream-VAD quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about FireRedVAD-Stream-VAD
How much VRAM does FireRedVAD-Stream-VAD need?
About 0.5 GB at its main file with an 8K context window. That is the 0.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run FireRedVAD-Stream-VAD on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FireRedVAD-Stream-VAD GGUF?
It depends on the quant: file is 0.0 GB, file is 0.0 GB, file is 0.0 GB.
Where can I download FireRedVAD-Stream-VAD GGUF?
The files are on Hugging Face in the cstr/firered-vad-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does FireRedVAD-Stream-VAD use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run FireRedVAD on 8 GB VRAM?
Yes, the unquantized GGUF model requires only 0.5 GB of VRAM at 8 k context, well within an 8 GB budget.
What audio format does FireRedVAD support?
It requires 16kHz 16‑bit mono PCM wav files. Convert other formats with ffmpeg.
Is FireRedVAD licensed for commercial use?
It is released under the Apache 2.0 license, which permits commercial use.