SP

TitaNet-Large

SpeakerverificationGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters22M
Context—
Layers—
Architecturetitanet
Smallest quant0.0 GB
Quick answer

TitaNet-Large 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.

TitaNet-Large: Speaker embedding extraction model

TitaNet-Large extracts speaker embeddings from 16000 Hz mono audio. It is a 23 M‑parameter model trained on English speech datasets such as VoxCeleb, Fisher, and Switchboard. The GGUF version is available for native C/C++ inference via CrispASR.

Good at

  • Speaker verification
  • Speaker diarization
  • Embedding extraction

Limits

  • No vision support
  • Requires 16000 Hz mono audio
  • CC‑BY‑4.0 license

Best for

  • Speaker enrollment
  • Speaker identification during transcription
  • Standalone embedding extraction

Who it’s for. Developers building speaker verification or diarization pipelines. Researchers needing a lightweight embedding extractor for English speech.

Quants & memory

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

The only available GGUF file is quantized as unknown, 0.04 GB. It requires approximately 0.5 GB of VRAM at 8 k context. This is suitable for systems with at least 1 GB VRAM. No other quants are provided.

What GPU do you need for TitaNet-Large?

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

Architecturetitanet
Parameters22M

Source

Quantized bycstr
Licensecc-by-4.0
Downloads (HF)1,418
Last updated2026-08-02

Frequently asked questions about TitaNet-Large

How much VRAM does TitaNet-Large 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 TitaNet-Large 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 TitaNet-Large GGUF?

It depends on the quant: file is 0.0 GB.

Where can I download TitaNet-Large GGUF?

The files are on Hugging Face in the cstr/titanet-large-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 TitaNet-Large use?

Hugging Face lists the license as cc-by-4.0. 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 TitaNet-Large on 8 GB VRAM?

Yes, the model needs about 0.5 GB VRAM at 8 k context, well below 8 GB.

What audio format does the model accept?

It accepts 16000 Hz mono‑channel WAV files.

Is the model licensed for commercial use?

It is licensed under CC‑BY‑4.0, which allows commercial use with attribution.

Other GGUFs of speakerverification_en_titanet_large

Similar models

Browse all →

More from cstr

All by cstr →

More Speakerverification models

All Speakerverification →

Other tiny models

All tiny models →