Model card for qwen3_vit_306m.qwen_drive_1_0_4b

A Qwen ViT image feature model extracted from Qwen-Drive-1.0-4B. This is the classifier-ready wrapper with average pooling and affine-free LayerNorm over the encoder features.

NOTE: This checkpoint is a native timm remap of the original vision weights, with no additional training. It contains no language-model weights or trained image-classification head.

Model Notes

• Image inputs repeat one frame across the original temporal patch kernel. The temporal Conv3d weights are summed into a Conv2d for this image-only implementation.
• The backbone uses GELU-tanh MLPs, learned absolute positions and axial 2D RoPE. Absolute positions are interpolated for the input grid; RoPE is regenerated at each size.
• The timm transforms normalize RGB pixels using mean=(0.5, 0.5, 0.5) and std=(0.5, 0.5, 0.5). Rectangular inputs are supported. Each image dimension must be divisible by 16; any variant using the 2×2 merger requires divisibility by 32.
• forward_features() returns raw, unnormalized NHWC backbone features. The _enc variant returns spatially merged tokens from forward(); the classifier variant returns pooled image embeddings until a classification head is added.

Model Details

• Model Type: Image Feature Encoder
• Model Stats:
  • Params (M): 305.5
  • GMACs: 959.1
  • Activations (M): 2607.0
  • Image size: 768 x 768
• Source revision: 28484089a7cc8c335cf5089fb0745cf7c49b6eaa
• License source: https://raw.githubusercontent.com/QwenLM/Qwen-Drive-1.0/28091c1532e869bc7aee91fc0aef6b3e6fd0b2e0/LICENSE
• Original: https://huggingface.co/Qwen/Qwen-Drive-1.0-4B
• License: Apache 2.0
• Backbone width: 1024
• Papers:
  • Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving: https://arxiv.org/abs/2609.00111
  • PyTorch Image Models: https://github.com/huggingface/pytorch-image-models

Model Usage

Image Features

import torch
import timm
from PIL import Image

model = timm.create_model('hf-hub:timm/qwen3_vit_306m.qwen_drive_1_0_4b', pretrained=True).eval()
data_config = timm.data.resolve_model_data_config(model)
transform = timm.data.create_transform(**data_config, is_training=False)
image = Image.open('image.jpg').convert('RGB')
x = transform(image).unsqueeze(0)

with torch.inference_mode():
    output = model(x)  # (1, 1024): image embeddings
    features = model.forward_features(x)  # (1, 48, 48, 1024): raw backbone features (NHWC)

Intermediate Feature Maps

with torch.inference_mode():
    maps = model.forward_intermediates(
        x, indices=3, output_fmt='NCHW', intermediates_only=True,
    )
for feature_map in maps:
    print(feature_map.shape)  # (1, 1024, 48, 48)

Classification Fine-tuning

model = timm.create_model(
    'hf-hub:timm/qwen3_vit_306m.qwen_drive_1_0_4b', pretrained=True, num_classes=45,
)
logits = model(x)  # (1, 45)

The new linear head is randomly initialized and must be trained on your target dataset.

Citation

@misc{zhou2026qwendrive10initialstepvisionlanguage,
  title={Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving},
  author={Xin Zhou and Zongchuang Zhao and Zhibo Yang and Mingsheng Li and Humen Zhong and Shuai Bai and Du Chu and Ruizhe Chen and Zhaohai Li and Jun Tang and Qiuyue Wang and Mingkun Yang and Jiazhao Zhang and Dayiheng Liu and Dingkang Liang and Xiang Bai},
  year={2026},
  eprint={2609.00111},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2609.00111}
}

@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}