VI

VibeVoice-7B

VibevoiceGGUF by audio-cppUpdated 2026-08-28
Download on Hugging Face
Parameters7B
Context—
Layers—
Architectureaudiocpp
Smallest quant10.6 GB
Quick answer

VibeVoice-7B needs about 12.4 GB of memory at Q8_0 (a 10.6 GB file) with an 8K context window, so it fits on a 16 GB GPU.

VibeVoice-7B: 7‑Billion‑parameter TTS for long‑form, multi‑speaker audio

VibeVoice-7B is a 7‑Billion‑parameter text‑to‑speech model built on the audiocpp architecture. It can generate up to 90 minutes of speech with up to four distinct speakers. The model uses continuous speech tokenizers and a diffusion head conditioned on a Qwen2.5 LLM.

Good at

  • Long‑form, multi‑speaker synthesis
  • High‑fidelity acoustic generation
  • Efficient 7.5 Hz tokenization

Limits

  • Requires 12.4 GB VRAM at 8 k context
  • No vision or non‑English language support
  • MIT license only

Best for

  • Podcast audio generation
  • Voice‑over production
  • Conversational AI demos

Who it’s for. Developers and content creators needing expressive, long‑form speech synthesis in English or Chinese. The model is suitable for applications that require multiple speakers and extended audio output.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_010.6 GB 12.4 GB
Too big Get file →

The only available quantization is Q8_0, 10.58 GB file size. It requires approximately 12.4 GB VRAM at 8 k context. For systems with less VRAM, no other quant is available. Use Q8_0 if your GPU can handle the memory requirement.

What GPU do you need for VibeVoice-7B?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q8_0 (10.6 GB file, about 12.4 GB in use).

Which VibeVoice-7B quant should you choose?

Q8_0 (10.6 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureaudiocpp
Parameters7B

Source

Quantized byaudio-cpp
FamilyVibevoice
Licensemit
Downloads (HF)42,359
Last updated2026-08-28

Frequently asked questions about VibeVoice-7B

How much VRAM does VibeVoice-7B need?

About 12.4 GB at Q8_0 with an 8K context window. That is the 10.6 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 VibeVoice-7B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of VibeVoice-7B GGUF?

It depends on the quant: Q8_0 is 10.6 GB.

Where can I download VibeVoice-7B GGUF?

The files are on Hugging Face in the audio-cpp/VibeVoice-7B-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 VibeVoice-7B 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 VibeVoice-7B on a GPU with 8 GB VRAM?

No. The Q8_0 quant requires about 12.4 GB VRAM at 8 k context, so 8 GB is insufficient.

Does VibeVoice-7B support Chinese?

Yes, the model is intended for English and Chinese speech synthesis.

Similar models

Browse all →

More from audio-cpp

All by audio-cpp →

More Vibevoice models

All Vibevoice →

Other small models

All small models →