You can deploy this model and start earning money today!

qualcomm/
Qwen3-4B

Name: Qwen3-4B
Availability: InStock

Views

No views yet

Qwen3-4B: Optimized for Qualcomm Devices

The Qwen3-4B is a state-of-the-art multilingual base language model with 4 billion parameters, excelling in language understanding, generation, coding, and mathematics.

This is based on the implementation of Qwen3-4B 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 Qwen3-4B on-device

Follow the GenieX quickstart to install GenieX and deploy the model on a target device.

See the LLM-on-Genie tutorial to run with the Genie runtime. Note: Genie support will be deprecated soon.

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	w4a16	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45	Download
GENIE	w4a16	Snapdragon® 8 Elite Mobile	QAIRT 2.45	Download
GENIE	w4a16	Snapdragon® X2 Elite	QAIRT 2.45	Download
GENIE	w4a16	Snapdragon® X Elite	QAIRT 2.45	Download
GENIE	w4a16	Qualcomm® Dragonwing™ IQ-8275	QAIRT 2.45	Download
GENIE	w4a16	Qualcomm® SA8775P	QAIRT 2.45	Download
GENIE	w4a16	Qualcomm® Dragonwing™ IQ-9075	QAIRT 2.45	Download
GENIEX_LLAMACPP	q4_0	Universal		Download
GENIEX_QAIRT	w4a16	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45	Download
GENIEX_QAIRT	w4a16	Snapdragon® 8 Elite Mobile	QAIRT 2.45	Download
GENIEX_QAIRT	w4a16	Snapdragon® X2 Elite	QAIRT 2.45	Download
GENIEX_QAIRT	w4a16	Snapdragon® X Elite	QAIRT 2.45	Download
GENIEX_QAIRT	w4a16	Qualcomm® Dragonwing™ IQ-8275	QAIRT 2.45	Download
GENIEX_QAIRT	w4a16	Qualcomm® Dragonwing™ IQ-9075	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit Qwen3-4B 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 Qwen3-4B on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

Response Rate: Rate of response generation after the first response token. Measured on a short prompt with a long response (with thinking); may slow down when using longer context lengths.
Supported languages: 100+ languages and dialects.
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).

Performance Summary

Model	Runtime	Precision	Chipset	Context Length	Response Rate (tokens per second)	Time To First Token (range, seconds)
Qwen3-4B	GENIE	w4a16	Snapdragon® 8 Elite Gen 5 Mobile	4096	29.241936683654785	0.051795499999999994 - 1.6574559999999998
Qwen3-4B	GENIE	w4a16	Snapdragon® 8 Elite Mobile	4096	24.391611099243164	0.06899839999999999 - 2.2079487999999996
Qwen3-4B	GENIE	w4a16	Snapdragon® X2 Elite	4096	30.268534088134764	0.06770319999999999 - 2.1665023999999997
Qwen3-4B	GENIE	w4a16	Qualcomm® Dragonwing™ IQ-9075	4096	17.71731367111206	0.10616810000000002 - 3.3973792000000005
Qwen3-4B	GENIE	w4a16	Qualcomm® Dragonwing™ Q-8750	4096	24.391611099243164	0.06899839999999999 - 2.2079487999999996
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® 8 Elite Mobile	512	22.345148	1.163462 - 4.653848
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® 8 Elite Mobile	512	21.837581	1.20320125 - 4.812805
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® 8 Elite Mobile	512	18.065555	0.24040424999999999 - 0.957415
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® 8 Elite Mobile	1024	19.048557	12.245683999999999 - 12.245683999999999
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® 8 Elite Mobile	1024	19.016666	12.59975 - 12.59975
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® 8 Elite Mobile	1024	16.243636	2.318602 - 2.318602
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® 8 Elite Mobile	4096	7.579774	3.2244959375 - 103.18387
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® 8 Elite Mobile	4096	8.135403	3.39820121875 - 108.742439
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® 8 Elite Mobile	4096	12.112907	0.48037071875 - 0.760079
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® X2 Elite	512	33.741473	0.27790575 - 1.111623
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® X2 Elite	512	33.490468	0.27597075 - 1.103883
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® X2 Elite	512	20.973144	0.16287725 - 0.651509
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® X2 Elite	4096	20.323515	0.5701374375 - 18.244398
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® X2 Elite	4096	20.262276	0.57165421875 - 18.292935
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® X2 Elite	4096	14.386503	0.2386385625 - 7.636434
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® X Elite	512	22.888754	0.74547975 - 2.981919
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® X Elite	512	22.661212	0.62115075 - 2.484603
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® X Elite	512	12.489915	0.37069175 - 1.482767
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® X Elite	4096	10.628056	1.4426614687500001 - 46.165167000000004
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® X Elite	4096	5.741986	1.5289054375 - 48.924974
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Snapdragon® X Elite	4096	7.732127	0.57647490625 - 18.447197
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ IQ-8275	512	3.89819	15.667422 - 62.669688
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ IQ-8275	512	2.541718	22.965225999999998 - 91.86090399999999
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ IQ-8275	512	9.177897	1.25627 - 5.02508
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ IQ-8275	4096	1.199191	182.91975399999998 - 5853.4321279999995
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ IQ-8275	4096	1.935562	283.76102000000003 - 9080.352640000001
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ IQ-8275	4096	5.080893	12.972363999999999 - 415.11564799999996
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ IQ-X7181	512	22.888754	0.74547975 - 2.981919
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ IQ-X7181	512	22.661212	0.62115075 - 2.484603
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ IQ-X7181	512	12.489915	0.37069175 - 1.482767
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ Q-8750	512	22.345148	1.163462 - 4.653848
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ Q-8750	512	21.837581	1.20320125 - 4.812805
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ Q-8750	512	18.065555	0.24040424999999999 - 0.957415
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ Q-8750	1024	19.048557	12.245683999999999 - 12.245683999999999
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ Q-8750	1024	19.016666	12.59975 - 12.59975
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ Q-8750	1024	16.243636	2.318602 - 2.318602
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ IQ-X7181	4096	10.628056	1.4426614687500001 - 46.165167000000004
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ IQ-X7181	4096	5.741986	1.5289054375 - 48.924974
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ IQ-X7181	4096	7.732127	0.57647490625 - 18.447197
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ Q-8750	4096	7.579774	3.2244959375 - 103.18387
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ Q-8750	4096	8.135403	3.39820121875 - 108.742439
Qwen3-4B	GENIEX_LLAMACPP	q4_0	Qualcomm® Dragonwing™ Q-8750	4096	12.112907	0.48037071875 - 0.760079
Qwen3-4B	GENIEX_QAIRT	w4a16	Snapdragon® 8 Elite Gen 5 Mobile	4096	28.561795	0.048449 - 1.550368
Qwen3-4B	GENIEX_QAIRT	w4a16	Snapdragon® 8 Elite Mobile	4096	26.796653	0.05923 - 1.89536
Qwen3-4B	GENIEX_QAIRT	w4a16	Snapdragon® X2 Elite	4096	38.620675	0.044926 - 1.437632
Qwen3-4B	GENIEX_QAIRT	w4a16	Snapdragon® X Elite	4096	21.220268	0.09903100000000001 - 3.1689920000000003
Qwen3-4B	GENIEX_QAIRT	w4a16	Qualcomm® Dragonwing™ IQ-8275	4096	16.769441	0.098417 - 3.149344
Qwen3-4B	GENIEX_QAIRT	w4a16	Qualcomm® Dragonwing™ IQ-9075	4096	18.556224	0.091569 - 2.930208
Qwen3-4B	GENIEX_QAIRT	w4a16	Qualcomm® Dragonwing™ IQ-X7181	4096	21.220268	0.09903100000000001 - 3.1689920000000003
Qwen3-4B	GENIEX_QAIRT	w4a16	Qualcomm® Dragonwing™ Q-8750	4096	26.796653	0.05923 - 1.89536

License

The license for the original implementation of Qwen3-4B can be found here.

References

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

qualcomm/Qwen3-4B