info.yaml

name: GenieX Chat Android
id: geniex_chat_android
license_url: https://github.com/qualcomm/nexa-sdk?tab=BSD-3-Clause-1-ov-file
license_type: bsd-3-clause
headline: Run LLMs and VLMs on Android with GenieX
description: 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.
runtime: [geniex_qairt, geniex_llamacpp]
status: published
domain: Generative AI
app_type: 'android'
use_case: Text Generation
related_models: [
  'qwen3_0_6b',
  'qwen3_1_7b',
  'ministral_3_3b_instruct_2512',
  'granite_4_0_micro',
  'phi_4_mini_instruct',
  'gemma_4_e2b_it',
  'gemma_4_e4b_it',
  'qwen3_5_0_8b',
  'qwen3_5_2b',
  'qwen3_vl_2b_instruct',
  'qwen3_vl_4b_instruct',
  'qwen3_4b',
  'qwen3_4b_instruct_2507',
  'qwen2_5_vl_7b_instruct',
]
precisions: []
static_img_filename: 'app_screen.png'
app_repo_relative_path: 'geniex_chat_android'
supported_devices: ["Snapdragon 8 Elite QRD", "Snapdragon 8 Elite Gen 5 QRD"]
base_docker: ubuntu.dockerfile
# This app downloads models at runtime via the GenieX SDK rather than bundling
disable_cli_model_fetch: true
os:
  name: Android
  version: 12+
languages: ['Kotlin', 'Java']