Downloads · 30 days
42
72% of all-time downloads
INT8-H16P
Omdano/INT8-H16P
INT8-H16P is a machine learning model from Omdano. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
INT8 quantized version of facebook/dinov3-vith16plus-pretrain-lvd1689m using BitsAndBytes.
All-time downloads
58
Public
Repo size
2.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin848 MB · 100%
At a glance
- Model type
- dinov3_vit
- Access
- Public
- Created
- Oct 5, 2025
- Updated
- Oct 5, 2025
- SHA
- c68d9697
Model card
From the Hugging Face model README
DinoV3 Vision Transformer Huge (INT8 Quantized)
INT8 quantized version of facebook/dinov3-vith16plus-pretrain-lvd1689m using BitsAndBytes.
Model Details
- Base Model: DinoV3 Vision Transformer Huge (840M parameters)
- Quantization: INT8 weight-only quantization via BitsAndBytes
- Size: ~845MB (from ~1.7GB original)
- Compression: ~2x size reduction
- Accuracy Loss: <1% typical
Usage
from transformers import AutoModel, BitsAndBytesConfig
# Load the INT8 quantized model
model = AutoModel.from_pretrained(
"Omdano/INT8-H16P",
trust_remote_code=True,
quantization_config=BitsAndBytesConfig(load_in_8bit=True),
device_map="auto"
)
# Use for feature extraction or classification
outputs = model(pixel_values=inputs)
Benefits
- 2x smaller than full precision model
- Faster inference on GPU
- Same API as original DinoV3
- Minimal accuracy loss (<1%)
Requirements
pip install transformers bitsandbytes torch
Original Model
Based on facebook/dinov3-vith16plus-pretrain-lvd1689m
License
Apache 2.0 (same as original DinoV3)
- Type
- dinov3_vit
- Created
- Oct 5, 2025
- Updated
- Oct 5, 2025