SI

Silero VAD v6.2

SileroGGUF by handy-computerUpdated 2026-10-16
Download on Hugging Face
Parameters—
Context—
Layers—
Architecturesilero_vad
Smallest quant0.0 GB
Quick answer

Silero VAD v6.2 needs about 0.5 GB of memory at F32 (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Silero VAD v6.2 – Voice activity detection model

Silero VAD v6.2 is a lightweight voice activity detection model. It outputs per‑frame speech probabilities and offline speech segments. The model is designed for use with transcribe.cpp.

Good at

  • Per‑frame speech probability detection
  • Offline speech segmentation
  • CPU‑friendly inference

Limits

  • No transcription capability
  • No vision support
  • Requires mono WAV at sample rate

Best for

  • Real‑time voice activity detection
  • Pre‑processing audio for transcription
  • Filtering non‑speech segments

Who it’s for. Developers building audio processing pipelines or applications that need to detect speech presence. The model is suitable for embedded or low‑resource environments due to its small memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F320.0 GB 0.5 GB
Fits Get file →

The only available quantization is F32. It requires approximately 0.5 GB of VRAM at 8k context. For systems with limited VRAM, consider using a smaller context or a different VAD model.

What GPU do you need for Silero VAD v6.2?

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 F32 (0.0 GB file, about 0.5 GB in use).

Which Silero VAD v6.2 quant should you choose?

F32 (0.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturesilero_vad

Source

Quantized byhandy-computer
FamilySilero
Licensemit
Downloads (HF)5,740
Last updated2026-10-16

Frequently asked questions about Silero VAD v6.2

How much VRAM does Silero VAD v6.2 need?

About 0.5 GB at F32 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 Silero VAD v6.2 on an 8 GB GPU?

Yes, with F32: 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 Silero VAD v6.2 GGUF?

It depends on the quant: F32 is 0.0 GB.

Where can I download Silero VAD v6.2 GGUF?

The files are on Hugging Face in the handy-computer/silero-vad-v6.2-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 Silero VAD v6.2 use?

Hugging Face lists the license as mit. 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 Silero VAD v6.2 on 1 GB VRAM?

The F32 quantization requires about 0.5 GB at 8k context, so 1 GB VRAM is sufficient for inference.

Does this model support multi‑channel audio?

No, it expects mono WAV input at the model's sample rate.

Is the model licensed for commercial use?

Yes, it is released under the MIT license, allowing commercial use.

More from handy-computer

All by handy-computer →

More Silero models

All Silero →