FS

fsmn vad

FsmnGGUF by FunAudioLLMUpdated 2026-06-21
Download on Hugging Face
Parameters—
Context—
Layers—
Architecturefsmn-vad
Smallest quant0.0 GB
Quick answer

fsmn 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.

FSMN-VAD – voice‑activity detection in a single GGUF binary

FSMN‑VAD is a GGUF build of FunASR’s voice‑activity detection model. It runs on the FunASR llama.cpp runtime, enabling long‑audio segmentation entirely in C++ without Python.

Good at

  • Fast VAD on CPU
  • Zero‑Python runtime
  • Edge deployment

Limits

  • No vision support
  • No training context info
  • License: apache‑2.0

Best for

  • Edge VAD on low‑resource devices
  • Batch audio segmentation
  • Real‑time voice detection

Who it’s for. Developers needing lightweight voice‑activity detection for edge or CPU‑only environments. Suitable for embedded systems, IoT, or any scenario where a single binary is preferred.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →

The only available quant is "unknown" with a file size of 0 GB and an estimated memory usage of 0.5 GB at 8 k context. This is suitable for devices with at least 1 GB of RAM. No other quants are provided.

What GPU do you need for fsmn 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).

Specifications

Architecture from the GGUF header

Architecturefsmn-vad

Source

Quantized byFunAudioLLM
FamilyFsmn
Licenseapache-2.0
Downloads (HF)2,402
Last updated2026-06-21

Frequently asked questions about fsmn vad

How much VRAM does fsmn 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 fsmn 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 fsmn vad GGUF?

It depends on the quant: file is 0.0 GB.

Where can I download fsmn vad GGUF?

The files are on Hugging Face in the FunAudioLLM/fsmn-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 fsmn 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 FSMN‑VAD on a machine with 1 GB of RAM?

Yes, the model requires approximately 0.5 GB of RAM at 8 k context, so 1 GB is sufficient.

Does FSMN‑VAD support GPU acceleration?

No, it is designed for CPU/edge use with the FunASR llama.cpp runtime.

More from FunAudioLLM

All by FunAudioLLM →

More Fsmn models

All Fsmn →