Model components / Inference code

ncnn

ncnn is a neural network inference runtime optimized for mobile, embedded and desktop deployment, with no third-party dependency in its core. It ships pnnx for converting PyTorch and ONNX models into its own format, and targets general neural network inference rather than LLM serving specifically.

The LICENSE.txt file states the terms for both the binary and the source, and also bundles third-party components under separate terms. Verified 2026-08-31 via GitHub, the LICENSE body and the repository README.

Openness

5 medium confidence

5.0

license: BSD-3-Clause(OSI)
source: public(the published repository is the engine)
core-gated: ungated(no enterprise path in the repository root and no paid build of the engine in the README)

The LICENSE body is a Tencent-authored notice stating that both the ncnn binary and the ncnn source are licensed under the BSD 3-Clause License, followed by the separate terms of third-party components it vendors, read in full rather than taken from the API's label. The repository is public and unarchived and builds the engine itself. Its root tree carries no enterprise, ee or commercial directory and its README describes no licence-gated build, so the core reads as ungated. Confidence is medium because that is a repository-and-README read rather than a pricing-page read.

https://raw.githubusercontent.com/Tencent/ncnn/master/LICENSE.txt recorded 2026-08-31
LICENSE body, read in full: a Tencent-authored notice stating that both the ncnn binary and the ncnn source are licensed under the BSD 3-Clause License, followed by the separate terms of third-party components it vendors.
https://api.github.com/repos/Tencent/ncnn recorded 2026-08-31
Repo metadata for Tencent/ncnn - archived false, 23,768 stars.
https://raw.githubusercontent.com/Tencent/ncnn/master/README.md recorded 2026-08-31
README, read for a paid tier, an enterprise edition or a licence-gated build beside the published source, and for whether any component is stated to be private.

Adoption

3 low confidence

3.0

23,768 GitHub stars, which lands in the >10K band of the stars scale, level 3, where the scale caps. An `ncnn` package on PyPI resolves to this repository but pypistats publishes no download figure for it, so no package artifact is declared and the band rests on stars.

https://api.github.com/repos/Tencent/ncnn recorded 2026-08-31
Repo metadata - stargazers_count = 23,768 - for Tencent/ncnn.

Capability

3 medium confidence

3.0

Two bands below the vllm anchor. Its platform reach is wide, but the anchor is banded on LLM serving - batching, paged attention, parallelism, an OpenAI-compatible surface - and this runtime provides none of that, which is why it sits with the other narrow-purpose runtimes rather than with onnx-runtime at one below.

https://raw.githubusercontent.com/Tencent/ncnn/master/README.md recorded 2026-08-31
README, read for the engine's feature set: General neural network inference across mobile, embedded and desktop targets, with a model conversion toolchain; not an LLM serving engine.

Verified 2026-08-31