VI

vibevoice

VibevoiceGGUF by gguf-orgUpdated 2025-09-08
Download on Hugging Face
Parameters2.7B
Context—
Layers—
Architecturepig
Smallest quant3.2 GB
Quick answer

vibevoice needs about 4.5 GB of memory at Q4_K_M (a 3.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 17 quants, from 3.2 GB (Q2_K) to 10.8 GB (F32).

VibeVoice 2.7B text‑to‑speech model for long, multi‑speaker audio

VibeVoice is a 2.7B parameter model that generates expressive, long‑form audio. It supports up to 90 minutes of speech and up to four distinct speakers. The model uses a diffusion head conditioned on an LLM to produce high‑fidelity acoustic details.

Good at

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

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • MIT license only for non‑commercial use

Best for

  • Podcast narration
  • Audiobook production
  • Voice cloning demos

Who it’s for. Developers and researchers building TTS applications that need extended audio and multiple speaker support. The model is suitable for local deployment via llama.cpp or gguf‑connector.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.2 GB 4.1 GB
Fits Get file →
IQ3_XXS3.3 GB 4.2 GB
Fits Get file →
IQ3_S3.4 GB 4.3 GB
Fits Get file →
Q3_K_M3.4 GB 4.3 GB
Fits Get file →
IQ4_XS3.5 GB 4.4 GB
Fits Get file →
IQ4_NL3.5 GB 4.5 GB
Fits Get file →
Q4_03.5 GB 4.5 GB
Fits Get file →
Q4_K_M3.5 GB 4.5 GB
Fits Get file →
Q4_13.6 GB 4.6 GB
Fits Get file →
Q5_03.7 GB 4.6 GB
Fits Get file →
Q5_K_M3.7 GB 4.6 GB
Fits Get file →
Q5_13.8 GB 4.7 GB
Fits Get file →
Q6_K3.9 GB 4.8 GB
Fits Get file →
Q8_04.2 GB 5.2 GB
Fits Get file →
F165.4 GB 6.6 GB
Fits Get file →
BF165.4 GB 6.6 GB
Fits Get file →
F3210.8 GB 12.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (3.54 GB file, ~4.5 GB memory). For 12 GB VRAM, Q8_0 (4.19 GB file, ~5.2 GB memory) is a good balance. If more memory is available, F16 (5.41 GB file, ~6.6 GB memory) offers higher precision.

What GPU do you need for vibevoice?

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: the best quant that fits is Q8_0 (4.2 GB file, about 5.2 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (5.4 GB file, about 6.6 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (5.4 GB file, about 6.6 GB in use).
  • 16 GB VRAM: the best quant that fits is F32 (10.8 GB file, about 12.6 GB in use).

Which vibevoice quant should you choose?

Q4_K_M is the usual starting point for vibevoice: it balances file size and quality well. Here it is a 3.5 GB file.

The Q8_0 file is 4.2 GB, about 1.2 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 3.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturepig
Parameters2.7B

Source

Quantized bygguf-org
FamilyVibevoice
Licensemit
Downloads (HF)2,079
Last updated2025-09-08

Frequently asked questions about vibevoice

How much VRAM does vibevoice need?

About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.5 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 on an 8 GB GPU?

Yes, with BF16: the 5.4 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of vibevoice GGUF?

It depends on the quant: Q2_K is 3.2 GB, IQ3_XXS is 3.3 GB, IQ3_S is 3.4 GB, Q3_K_M is 3.4 GB, IQ4_XS is 3.5 GB, IQ4_NL is 3.5 GB and 11 more.

Where can I download vibevoice GGUF?

The files are on Hugging Face in the gguf-org/vibevoice-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 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 on 8 GB VRAM?

Yes, the Q4_K_M quantization uses about 4.5 GB of VRAM at 8 k context, which fits within an 8 GB budget.

Does VibeVoice support voice cloning?

Yes, the demo supports cloning two voices by providing reference audio samples.

Other GGUFs of VibeVoice-1.5B

Similar models

Browse all →

More from gguf-org

All by gguf-org →

More Vibevoice models

All Vibevoice →

Other tiny models

All tiny models →