Qualcomm® AI HubAI Hub
Automotive

Automotive

Unlocking a New Era of Mobility

New to Models? Get started with our tutorial.

Models

590 variants · 225 models
View details for the Llama-v3.2-1B-Instruct model.

Llama-v3.2-1B-Instruct

State-of-the-art large language model useful on a variety of language understanding and generation tasks.

View details for the Llama-v3.2-3B-Instruct model.

Llama-v3.2-3B-Instruct

State-of-the-art large language model useful on a variety of language understanding and generation tasks.

View details for the Llama-v3.2-3B-Instruct-SSD model.

Llama-v3.2-3B-Instruct-SSD

State-of-the-art large language model useful on a variety of language understanding and generation tasks, with Self Speculative Decoding offering faster token rates.

View details for the ACT model.

ACT

Action Chunking with Transformers.

View details for the Albert-Base-V2-Hf model.

Albert-Base-V2-Hf

Language model for masked language modeling and general-purpose NLP tasks.

View details for the AOT-GAN model.

AOT-GAN

High resolution image in-painting on-device.

View details for the Beit model.

Beit

Imagenet classifier and general purpose backbone.

View details for the Bert-Base-Uncased-Hf model.

Bert-Base-Uncased-Hf

Language model for masked language modeling and general-purpose NLP tasks.

View details for the BEVDet model.

BEVDet

Construct a bird’s eye view from sensors mounted on a vehicle.

View details for the BEVFormer model.

BEVFormer

Transform temporal multi-view images into a unified bird's eye scene.

View details for the BEVFusion model.

BEVFusion

Construct a bird’s eye view from sensors mounted on a vehicle.

View details for the CavaFace model.

CavaFace

Comprehensive facial analysis by extracting face features.