qualcomm / GenieX
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
Why this job: topics: local-ai, on-device-ai
What it does
GenieX is an on-device Gen AI inference runtime for Qualcomm devices. Bring almost any GGUF model from Hugging Face, ModelScope, or Docker Hub, or use a pre-compiled bundle from Qualcomm AI Hub. Run it locally on the Hexagon NPU, Adreno GPU, or CPU in a few lines of code. One C SDK underneath is exposed through a CLI, Python, Kotlin/Java, Docker, and an OpenAI-compatible server. It is the community version of Qualcomm GENIE.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 4 days ago
- Stars
- 8,509
- +26 this week
- Licence
- BSD-3-Clause
- Allows business use
- Downloads for
- 2 systems
- Windows, Linux
- Latest version
- v0.10.0
- Released 12 days ago
- Built with
- Go
- 30% of the code
Is it looked after?
- Contributors
- 9
- Last 90 days
- Issues
- 87% closed
- 56 still open
- Pull requests
- 1,087 merged
- 31 waiting
- Releases
- 79
- 30+ in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| drumih / turbo-fieldfare | 7,321 | 14 days ago | Apache-2.0 | No downloads |
| carloslfu / slotstream | 659 | today | MIT | No downloads |
More: download files, languages, topics and project record
Download files, v0.10.0
- Windows6 files, 551 downloads
- Linux10 files, 136 downloads
Languages
- Go 30%
- Rust 22%
- C++ 18%
- Python 16%
Topics
- llm
- on-device-ai
- sdk
- vlm
- go
- gpt-oss
- llama3
- qwen3
- granite4
- qwen3vl
- gemma4
- hexagon
Project record
- JobLocal LLMs
- StatusListed
- Commits2,644
- Forks1,078
- Watching531
- Stars in 28 days+90
- CreatedAug 16, 2024
- First seen by usNov 7, 2026
- CheckedNov 9, 2026