2026-07-07 22:44 UTCIn-site rewrite4 min readUpdated: 2026-07-07 22:50 UTC

Qualcomm acquires Nexa AI, open-sources GenAI runtime for Hexagon NPUs

Qualcomm has acquired Nexa AI and open-sourced GenieX, a GenAI runtime optimized for Hexagon NPUs. It enables running LLMs and VLMs locally on Snapdragon devices via CLI, Python, Kotlin/Java, Docker, and an OpenAI-compatible server, supporting both Hugging Face GGUF models and Qualcomm AI Hub bundles.

SourceHacker News AIAuthor: BUFU

Uh oh!

There was an error while loading. Please reload this page.

Notifications You must be signed in to change notification settings

Fork 1k

Star 8.2k

BranchesTags

Open more actions menu

Folders and files

NameName

Last commit message

Last commit date

Latest commit

History

1,729 Commits

.claude

.github

bindings

cli

docs

examples/python

notes

scripts

sdk

tests

third-party

.bazelignore

.bazelrc

.bazelversion

.clang-format

.gitattributes

.gitignore

.gitmodules

.mailmap

BUILD.bazel

CLAUDE.md

CODE-OF-CONDUCT.md

CODEOWNERS

CONTRIBUTING.md

GenieX-Logo-Hor-1-Black.png

GenieX-Logo-Hor-1-White.png

LICENSE

MODULE.bazel

MODULE.bazel.lock

NOTICE

README.md

README_zh-CN.md

SECURITY.md

repolint.json

Repository files navigation

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.

Platform Example devices Jump to a quickstart

🪟 Windows ARM64 (Compute) Snapdragon X · X Elite CLI · Python · Local server

🤖 Android (Mobile) Snapdragon 8 Elite · 8 Elite Gen 5 Android SDK

🐧 Linux ARM64 (IoT) Dragonwing QCS9075 CLI · Docker · Python

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

📖 Docs — Install · Quickstart · Command reference

Python

Install

pip install geniex

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.

llama.cpp (llama_cpp) Qualcomm AI Engine Direct (qairt)

Get models from Hugging Face (any GGUF) Qualcomm AI Hub (pre-compiled)

Format GGUF Per-chipset bundle

Compute units NPU · GPU · CPU NPU only

Best for Bringing your own GGUF Highest NPU performance

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.

🏗️ Build the CLI, SDK, or Python bindings notes/build.md

▶️ Run & select compute units / pull models notes/run.md

🏷️ Release — SemVer tags, channels, HTP signing notes/release.md

📚 All developer docs docs/README.md

💬 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.

About

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

geniex.aihub.qualcomm.com/en/get-started/what-is-geniex

Topics

sdk

hexagon

snapdragon

qualcomm

vlm

on-device-ai

llm

local-ai

llama3

qwen3

gpt-oss

granite4

qwen3vl

gemma4

Resources

Readme

License

BSD-3-Clause license

Code of conduct

Contributing

Security policy

Uh oh!

There was an error while loading. Please reload this page.

Activity

Custom properties

Stars

8.2k stars

Watchers

525 watching

Forks

1k forks

Report repository

Releases 60

v0.3.14

Latest

Jul 2, 2026

+ 59 releases

Packages 0

Uh oh!

There was an error while loading. Please reload this page.

Uh oh!

There was an error while loading. Please reload this page.

Contributors

Uh oh!

There was an error while loading. Please reload this page.

Languages

Rust 25.8%

C++ 21.2%

Python 19.1%

Go 16.4%

C 8.5%

Kotlin 2.5%

Other 6.5%