Downloads · 30 days
0
VibeVoice7b-low-vram
DevParker/VibeVoice7b-low-vram
VibeVoice7b-low-vram is a text-to-speech model from DevParker. Use it when you need text read aloud. It is set up for vibevoice. The card lists the license as mit.
Pre-quantized versions of VibeVoice 7B for low VRAM GPUs.
Access
Public
Updated Oct 23, 2025
Repo size
17.2 GB
Likes
75
Public
Repo makeup
Click a slice to open those files.
.safetensors6.6 GB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- vibevoice
- License
- mit
- Access
- Public
- Created
- Aug 31, 2025
- Updated
- Oct 23, 2025
- SHA
- 5842b770
Model card
From the Hugging Face model README
VibeVoice 7B - Low VRAM Quantized Models
Pre-quantized versions of VibeVoice 7B for low VRAM GPUs.
Available Versions
- 4bit/ - 4-bit quantized model (~8GB VRAM needed)
- 8bit/ - 8-bit quantized model (~12GB VRAM needed) - NOTE: Removed 8 bit until I can test it again. I'll re-up it soon.
Usage
from vibevoice.modular.modeling_vibevoice_inference import VibeVoiceForConditionalGenerationInference
from vibevoice.processor.vibevoice_processor import VibeVoiceProcessor
# For 4-bit model
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")
VRAM Requirements
- 4-bit: ~8 GB total VRAM
- 8-bit: ~12 GB total VRAM
- Original: ~19 GB total VRAM
See individual model folders for detailed information.
- Task
- Text-to-Speech
- Library
- vibevoice
- License
- mit
- Languages
- en
- Created
- Aug 31, 2025
- Updated
- Oct 23, 2025