VibeVoice-1.5B needs about 4.0 GB of memory at Q8_0 (a 3.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.9 GB (Q4_K) to 5.4 GB (F16).
VibeVoice-1.5B: Multi‑speaker TTS with up to 90‑minute synthesis
VibeVoice-1.5B is a text‑to‑speech model that supports voice cloning and multi‑speaker synthesis. It can generate up to 90 minutes of audio with up to 4 distinct speakers. The model uses a Qwen2.5‑1.5B LLM backbone and a diffusion head for acoustic detail.
Good at
- Long‑form audio up to 90 minutes
- Multi‑speaker synthesis up to 4 speakers
- Voice cloning from 24 kHz mono WAV
Limits
- No vision support
- Requires voice reference audio
- Context length up to 65,536 tokens
Best for
- Podcast generation
- Audiobook narration
- Virtual assistant voice cloning
Who it’s for. Developers building conversational audio applications or content creators needing expressive, multi‑speaker speech. The model is open‑source under MIT and can be run locally with GGUF conversion.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 1.9 GB | 2.6 GB | Fits | Get file → | |
| Q8_0 | 3.1 GB | 4.0 GB | Fits | Get file → | |
| F16 | 5.4 GB | 6.6 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K file (1.89 GB, ~2.6 GB memory at 8k context). For 12 GB VRAM, the Q8_0 file (3.12 GB, ~4 GB memory) is suitable. If more memory is available, the F16 file (5.41 GB, ~6.6 GB memory) provides full precision.
What GPU do you need for VibeVoice-1.5B?
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 Q8_0 (3.1 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.1 GB file, about 4.0 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (5.4 GB file, about 6.6 GB in use).
Which VibeVoice-1.5B quant should you choose?
Q8_0 (3.1 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.
If memory is tight, the smallest file is Q4_K at 1.9 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about VibeVoice-1.5B
How much VRAM does VibeVoice-1.5B need?
About 4.0 GB at Q8_0 with an 8K context window. That is the 3.1 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-1.5B on an 8 GB GPU?
Yes, with F16: 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-1.5B GGUF?
It depends on the quant: Q4_K is 1.9 GB, Q8_0 is 3.1 GB, F16 is 5.4 GB.
Where can I download VibeVoice-1.5B GGUF?
The files are on Hugging Face in the cstr/vibevoice-1.5b-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-1.5B 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-1.5B on 8 GB VRAM?
Yes, the Q4_K quantized model requires about 2.6 GB of VRAM at 8k context, which fits within 8 GB.
Does VibeVoice support voice cloning?
Yes, it requires a 24 kHz mono WAV file as a voice reference for cloning.