Qwen2.5-1.5B-Instruct: Optimized for Qualcomm Devices

The Qwen2.5-1.5B-Instruct is a state-of-the-art multilingual language model with 1.5 billion parameters, excelling in language understanding, generation, coding, and mathematics.

This is based on the implementation of Qwen2.5-1.5B-Instruct found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Deploying Qwen2.5-1.5B-Instruct on-device

Please follow the LLM on-device deployment tutorial.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime	Precision	Chipset	SDK Versions	Download
GENIE	w4	qualcomm-qcs8275	QAIRT 2.37	Download

For more device-specific assets and performance metrics, visit Qwen2.5-1.5B-Instruct on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

• Custom weights (e.g., fine-tuned checkpoints)
• Custom input shapes
• Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for Qwen2.5-1.5B-Instruct on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

• Input sequence length for Prompt Processor: 128
• Context length: 4096
• Precision: w4 + w8 (few layers) with fp16 activations
• Supported languages: Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
• TTFT: Time To First Token is the time it takes to generate the first response token. This is expressed as a range because it varies based on the length of the prompt. The lower bound is for a short prompt (up to 128 tokens, i.e., one iteration of the prompt processor) and the upper bound is for a prompt using the full context length (4096 tokens).
• Response Rate: Rate of response generation after the first response token.

Performance Summary

Model	Runtime	Precision	Chipset	Context Length	Response Rate (tokens per second)	Time To First Token (range, seconds)
Qwen2.5-1.5B-Instruct	GENIE	w4	Snapdragon® 8 Elite Mobile	4096	23.48920135498047	0.09537269999999999 - 3.0519263999999997
Qwen2.5-1.5B-Instruct	GENIE	w4	Snapdragon® X Elite	4096	12.98912	0.16027780000000003 - 5.128889600000001

License

• The license for the original implementation of Qwen2.5-1.5B-Instruct can be found here.

References

• Qwen2.5 Technical Report
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.

Usage and Limitations

This model may not be used for or in connection with any of the following applications:

• Accessing essential private and public services and benefits;
• Administration of justice and democratic processes;
• Assessing or recognizing the emotional state of a person;
• Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
• Education and vocational training;
• Employment and workers management;
• Exploitation of the vulnerabilities of persons resulting in harmful behavior;
• General purpose social scoring;
• Law enforcement;
• Management and operation of critical infrastructure;
• Migration, asylum and border control management;
• Predictive policing;
• Real-time remote biometric identification in public spaces;
• Recommender systems of social media platforms;
• Scraping of facial images (from the internet or otherwise); and/or
• Subliminal manipulation