GenieX Chat Android
Run LLMs and VLMs on Android with GenieX
A sample Android chat app that runs Large Language Models and Vision‑Language Models on‑device with the Qualcomm® GenieX SDK, using a single pluggable runtime that targets the Snapdragon® NPU, GPU, or CPU.
Compatible Models
Gemma-4-E2B-it
Lightweight multimodal model from Google DeepMind handling text and image input.
Gemma-4-E4B-it
Multimodal model from Google DeepMind handling text and image input.
GPT-OSS-20B
State-of-the-art Mixture of Experts large language model with extended context length for text generation tasks.
Granite-4.0-Micro
Compact language model from IBM optimized for enterprise tasks.
Ministral-3-3B-Instruct-2512
Efficient 3B parameter instruction-tuned model from Mistral AI.
Phi-4-Mini-Instruct
State-of-the-art large language model useful on a variety of language understanding and generation tasks.
Qwen2.5-VL-7B-Instruct
State-of-the-art vision-language model capable of understanding images and generating text responses.
Qwen3-0.6B
State-of-the-art large language model useful on a variety of language understanding and generation tasks.
Qwen3-1.7B
Multilingual 1.7B parameter language model excelling in reasoning and code generation.
Qwen3-4B
State-of-the-art large language model useful on a variety of language understanding and generation tasks.
Qwen3-4B-Instruct-2507
State-of-the-art large language model with instruct-only training, useful on a variety of language understanding and generation tasks.
Qwen3-VL-2B-Instruct
Multimodal 2B vision-language model capable of understanding text and images.
Qwen3-VL-4B-Instruct
Multimodal 4B vision-language model with enhanced visual reasoning capabilities.
Qwen3.5-0.8B
Ultra-compact 0.8B parameter model from the Qwen3.5 series for edge deployment.
Qwen3.5-2B
Balanced 2B parameter model from the Qwen3.5 series for on-device inference.
Information
Operating System
Android 12+Languages
Kotlin, JavaRuntime
Use Case
Join Us on Slack
