Qualcomm AI Hub
Qualcomm's official on-device-AI compiler + model zoo for Snapdragon NPU targets. Pre-quantized model variants for Llama, Phi, Gemma, Qwen running on Hexagon NPU. The reference path for Android NPU acceleration in 2025-2026.
Overview
Qualcomm's official on-device-AI compiler + model zoo for Snapdragon NPU targets. Pre-quantized model variants for Llama, Phi, Gemma, Qwen running on Hexagon NPU. The reference path for Android NPU acceleration in 2025-2026.
Featured in this stack
The L3 execution stacks that pick this tool as a recommended component, with the one-line note explaining the role it plays in each.
- Stack · L3·Homelab tier·Role: Snapdragon NPU runtime (Hexagon path)Android on-device AI stack — Phi-3.5 Mini / Llama 3.2 3B via MLC LLM or Qualcomm AI Hub
Qualcomm-published quants tuned for Hexagon NPU. The throughput leader on Snapdragon flagship phones — beats MLC LLM Adreno path by ~30-50% per Qualcomm's published numbers. Snapdragon-only; no Tensor G4 / MediaTek support.
Pros
- Vendor-published quants tuned for Hexagon NPU, with on-device performance data published on AI Hub
- Pre-compiled binaries for production Android apps
- Snapdragon X PC support unifies the toolchain across phone + Copilot+ PC
Cons
- Compilation runs on Qualcomm's hosted Workbench service; the model recipes in qualcomm/ai-hub-models are BSD-3
- Snapdragon-only — no MediaTek / Tensor G4 / Apple support
- Community resource density behind MLC LLM
Compatibility
| Operating systems | Android Windows Linux |
| GPU backends | Qualcomm Hexagon NPU Adreno |
| License | Closed source · free for hosted compilation; runtime free |
Runtime health
Operator-grade signals on how actively Qualcomm AI Hub is being maintained, how fresh its measurements are, and what failure classes operators have flagged. Every label below is anchored to a real date or count — we never infer maintainer activity we can't show.
Release cadence
Derived from the most recent editorial signal on this row.
2 days since last refresh · source: lastUpdated
Benchmark freshness
How recent the editorial measurements on this runtime are.
No editorial benchmarks for this runtime yet.
Community reproduction
Submissions that match an editorial measurement on similar hardware.
No community reproductions on file yet.
Get Qualcomm AI Hub
Frequently asked
Is Qualcomm AI Hub free?
What operating systems does Qualcomm AI Hub support?
Which GPUs work with Qualcomm AI Hub?
Reviewed by RunLocalAI Editorial. See our editorial policy for how we evaluate tools.
Related — keep moving
Verify Qualcomm AI Hub runs on your specific hardware before committing money.