GitHub - qualcomm/GenieX: Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

The easiest way to run frontier LLMs & VLMs locally on Qualcomm devices

Documentation · Quickstart · Models · Community

GenieX is an on-device Gen AI inference runtime for Qualcomm devices. Bring almost any GGUF model from Hugging Face — or a pre-compiled bundle from Qualcomm AI Hub — and run it locally on the Hexagon NPU, Adreno GPU, or CPU in a few lines of code. One C SDK underneath, exposed through a CLI, Python, Kotlin/Java, Docker, and an OpenAI-compatible server. It is the community version of Qualcomm GENIE.

Supported platforms

GenieX runs only on Qualcomm Snapdragon. Find your platform, then jump straight to the interface you want to use.

No device on hand? Spin up a remote session on Qualcomm Device Cloud.

Quickstart

Pick your interface below. Each one follows the same three steps — Install, Run, and Docs — and shows both runtimes: a GGUF model from Hugging Face (llama_cpp) and a pre-compiled bundle from Qualcomm AI Hub (qairt, NPU).

CLI

Install

• Windows ARM64 — download the installer, run it, then open a new terminal.
• Linux ARM64 — one line, no sudo:

  curl -fsSL https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-geniex/install.sh | sh

Run — chat with any model in one line (drag in an image for VLMs):

# GGUF from Hugging Face → llama.cpp (NPU / GPU / CPU)
geniex infer google/gemma-4-E4B-it-qat-q4_0-gguf

# Pre-compiled bundle from Qualcomm AI Hub → Qualcomm AI Engine Direct (NPU)
geniex infer ai-hub-models/Qwen2.5-VL-7B-Instruct

# GGUF from Docker Hub (https://hub.docker.com/u/ai) → llama.cpp (NPU / GPU / CPU)
geniex infer docker.io/ai/gemma3

📖 Docs — Install · Quickstart · Command reference

Python

Install

Run — mirrors Hugging Face transformers (from_pretrained() → .generate()):

# GGUF from Hugging Face → llama.cpp
from geniex import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3.5-2B-GGUF", precision="Q4_0")

messages = [{"role": "user", "content": "What is 2+2?"}]
prompt = model.tokenizer.apply_chat_template(messages, add_generation_prompt=True)

for chunk in model.generate(prompt, max_new_tokens=256, stream=True):
    print(chunk, end="", flush=True)

model.close()

# Pre-compiled bundle from Qualcomm AI Hub → Qualcomm AI Engine Direct (NPU)
from geniex import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("ai-hub-models/Qwen3-4B")

messages = [{"role": "user", "content": "What is 2+2?"}]
prompt = model.tokenizer.apply_chat_template(messages, add_generation_prompt=True)

for chunk in model.generate(prompt, max_new_tokens=256, stream=True):
    print(chunk, end="", flush=True)

model.close()

📖 Docs — Install · Quickstart · API reference

OpenAI-compatible server

Install — ships with the CLI (install above).

Run — pull any model (GGUF or Qualcomm AI Hub bundle), then serve an OpenAI-compatible API:

geniex pull ai-hub-models/Qwen3-4B-Instruct-2507
geniex serve   # serves http://127.0.0.1:18181/v1

curl http://127.0.0.1:18181/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ai-hub-models/Qwen3-4B-Instruct-2507",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Point any OpenAI client at http://127.0.0.1:18181/v1 — no code changes.

📖 Docs — Local server guide

Android (Kotlin / Java)

Install — add the SDK to your app module's build.gradle.kts:

dependencies {
    implementation("com.qualcomm.qti:geniex-android:0.3.1")
}

Run — fastest path is the sample app (chat UI, model picker for GGUF + Qualcomm AI Hub bundles, VLM support):

The Android demo app lives in qualcomm/ai-hub-apps. Clone it, open the sample app in Android Studio, and hit Run.

📖 Docs — Install · Quickstart · API reference

Docker

Install

docker pull docker.io/qualcomm/geniex:latest

Run — the container wraps the CLI, so geniex infer … works exactly as above.

📖 Docs — Docker guide

C / C++ SDK

Install — link against the single C header sdk/include/geniex.h; every other interface is a thin wrapper over it.

📖 Docs — sdk/README.md · notes/build.md

Models

GenieX has two runtimes so you get broad model coverage and peak Snapdragon performance in one stack. Both LLMs and VLMs are supported.

For llama.cpp, pick the Q4_0 precision when prompted — it has the best Hexagon NPU support. See the Models guide → for the full list, precisions, and how to run a local model.

🤝 Contributing

Contributions are welcome! Before opening a PR, please read CONTRIBUTING.md for branch naming, commit / PR title format, pre-commit checks, and the FFI-update rule for public SDK headers.

💬 Community & Contact

Questions, ideas, or want to show off what you built? Come say hi.

• 💬 Slack — ask questions and chat with the community in real time.
• 🐛 GitHub Issues — report a bug or request a feature.
• 🔗 LinkedIn — follow Qualcomm AI Hub for news and updates.

Contributors

Thanks to everyone building GenieX 💙

📄 License

BSD 3-Clause — see LICENSE and NOTICE.

Use of this project is also subject to Qualcomm's Terms of Use.