AI Potluck
Infrastructure / Compilers & Model Optimization

AIMET

Qualcomm

AIMET (AI Model Efficiency Toolkit) quantizes and compresses trained models to cut the compute and memory they need on edge devices such as phones and laptops. It works on PyTorch and ONNX models and combines post-training techniques with fine-tuning that recovers accuracy lost to quantization. Qualcomm Innovation Center develops it.

Verified 2026-08-18 via the GitHub API and the LICENSE body.

Openness

5 high confidence
5.0
license
BSD-3-Clause(OSI)
source
public
core-gated
ungated

BSD-3-Clause license body confirmed. The repository is public and unarchived and builds the whole product, and the README describes no paid tier, enterprise edition or license-gated build beside it, so source is public and the core ungated. GitHub reports the license as NOASSERTION because the LICENSE body opens with a Qualcomm Innovation Center copyright line; the body itself is the verbatim three-clause BSD text, which is what the tier reads.

  • https://github.com/qualcomm/aimet/blob/develop/LICENSE recorded 2026-08-18

    LICENSE body read rather than trusting the GitHub label: it opens with a Qualcomm Innovation Center copyright line and then runs the verbatim three-clause BSD text, which is why the API reports NOASSERTION.

  • https://api.github.com/repos/qualcomm/aimet recorded 2026-08-18

    Repo metadata - license spdx_id NOASSERTION, private false, archived false, default branch develop - for qualcomm/aimet.

  • https://github.com/qualcomm/aimet/blob/develop/README.md recorded 2026-08-18

    README describes post-training and fine-tuning quantization and compression of PyTorch and ONNX models to cut compute load and memory footprint for deployment on edge devices, with no paid tier, enterprise edition or license-key-gated build beside it.

Adoption

2 high confidence
2.0

23,007 PyPI downloads of `aimet-torch` in the trailing 30 days, which lands in the 10K-100K band of the software usage scale, level 2.

Capability

3 medium confidence
3.0

Banded on the category feature matrix as one optimization family, applied broadly. Placed two bands below the apache-tvm anchor, on a matrix that bands on how much of the model-to-hardware transformation pipeline a product performs, over how many inputs and targets.

Verified 2026-08-18