VibeVoice-Large-Q8

Results

• ✅ Perfect audio, identical to the original model
• ✅ 11.6 GB instead of 18.7 GB (-38%)
• ✅ Uses ~12 GB VRAM instead of 20 GB
• ✅ Works on 12 GB GPUs (RTX 3060, 4070 Ti, etc.)

🚨 The Problem with Other 8-bit Models

Most 8-bit models you'll find online quantize everything aggressively: Result: Audio components get quantized → numerical errors propagate → audio = pure noise.

✅ The Solution: Selective Quantization

I only quantized what can be safely quantized without losing quality.

Result: 52% of parameters quantized, 48% at full precision = perfect audio quality.

📊 Quick Comparison

+1.0 GB vs other 8-bit models = perfect audio instead of noise. Worth it.

💻 How to Use It

With Transformers

from transformers import AutoModelForCausalLM, AutoProcessor
import torch
import scipy.io.wavfile as wavfile

# Load model
model = AutoModelForCausalLM.from_pretrained(
    "FabioSarracino/VibeVoice-Large-Q8",
    device_map="auto",
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
)

processor = AutoProcessor.from_pretrained(
    "FabioSarracino/VibeVoice-Large-Q8",
    trust_remote_code=True
)

# Generate audio
text = "Hello, this is VibeVoice speaking."
inputs = processor(text, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=None)

# Save
audio = output.speech_outputs[0].cpu().numpy()
wavfile.write("output.wav", 24000, audio)

With ComfyUI (recommended)

1. Install the custom node:

   cd ComfyUI/custom_nodes
   git clone https://github.com/Enemyx-net/VibeVoice-ComfyUI
   

2. Download this model to ComfyUI/models/vibevoice/

3. Restart ComfyUI and use it normally!

💾 System Requirements

Minimum

• VRAM: 12 GB
• RAM: 16 GB
• GPU: NVIDIA with CUDA (required)
• Storage: 11 GB

Recommended

• VRAM: 16+ GB
• RAM: 32 GB
• GPU: RTX 3090/4090, A5000 or better

⚠️ Not supported: CPU, Apple Silicon (MPS), AMD GPUs

⚠️ Limitations

1. Requires NVIDIA GPU with CUDA - won't work on CPU or Apple Silicon
2. Inference only - don't use for fine-tuning
3. Requires:
   • transformers>=4.51.3
   • bitsandbytes>=0.43.0

🆚 When to Use This Model

✅ Use this 8-bit if:

• You have 12-16 GB VRAM
• You want maximum quality with reduced size
• You need a production-ready model
• You want the best size/quality balance

Use full precision (18.7 GB) if:

• You have unlimited VRAM (24+ GB)
• You're doing research requiring absolute precision

Use 4-bit NF4 (~6.6 GB) if:

• You only have 8-10 GB VRAM
• You can accept a small quality trade-off

🔧 Troubleshooting

"OutOfMemoryError" during loading

• Close other GPU applications
• Use device_map="auto"
• Reduce batch size to 1

"BitsAndBytes not found"

pip install bitsandbytes>=0.43.0

Audio sounds distorted

This shouldn't happen! If it does:

1. Verify you downloaded the correct model
2. Update transformers: pip install --upgrade transformers
3. Check CUDA: torch.cuda.is_available() should return True

📚 Citation

@misc{vibevoice-q8-2025,
  title={VibeVoice-Large-Q8: Selective 8-bit Quantization for Audio Quality},
  author={Fabio Sarracino},
  year={2025},
  url={https://huggingface.co/FabioSarracino/VibeVoice-Large-Q8}
}

Original Model

@misc{vibevoice2024,
  title={VibeVoice: High-Quality Text-to-Speech with Large Language Models},
  author={Microsoft Research},
  year={2024},
  url={https://github.com/microsoft/VibeVoice}
}

🔗 Related Resources

• Original Model - Full precision base
• ComfyUI Node - ComfyUI integration

📜 License

MIT License.

🤝 Support

• Issues: GitHub Issues
• Questions: HuggingFace Discussions

If this model helped you, leave a ⭐ on GitHub!

Created by Fabio Sarracino

The first 8-bit VibeVoice model that actually works

🤗 HuggingFace • 💻 GitHub