Downloads · 30 days
85
7% of all-time downloads
VibeVoice7b-low-vram-4bit
SomeoneSomething/VibeVoice7b-low-vram-4bit
VibeVoice7b-low-vram-4bit is a machine learning model from SomeoneSomething. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Optimized for RTX 3060/4060 and similar 12GB VRAM GPUs.
All-time downloads
1.2K
Public
Parameters
9.6B
6.6 GB on disk
Likes
10
Public
Repo makeup
Click a slice to open those files.
.safetensors6.6 GB · 100%
Parameter types
How the weights are stored.
U88.4B · 87%
Model card
From the Hugging Face model README
VibeVoice 7B - 4-bit Quantized
Optimized for RTX 3060/4060 and similar 12GB VRAM GPUs.
Specifications
- Quantization: 4-bit (nf4)
- Model size: 6.2 GB
- VRAM usage: ~8 GB
- Quality: Very good (minimal degradation)
Usage
from vibevoice.modular.modeling_vibevoice_inference import VibeVoiceForConditionalGenerationInference
from vibevoice.processor.vibevoice_processor import VibeVoiceProcessor
model = VibeVoiceForConditionalGenerationInference.from_pretrained(
"Dannidee/VibeVoice7b-low-vram/4bit",
device_map='cuda',
torch_dtype=torch.bfloat16,
)
processor = VibeVoiceProcessor.from_pretrained("Dannidee/VibeVoice7b-low-vram/4bit")
# Generate speech
text = "Speaker 1: Hello! Speaker 2: Hi there!"
inputs = processor(
text=[text],
voice_samples=[["voice1.wav", "voice2.wav"]],
padding=True,
return_tensors="pt",
)
outputs = model.generate(**inputs)
processor.save_audio(outputs.speech_outputs[0], "output.wav")
- Type
- vibevoice
- Created
- Sep 4, 2025
- Updated
- Sep 4, 2025