Comparison
FeatherCNN vs ncnn
Verdict
Pick FeatherCNN if featherCNN is optimized for ARM CPUs and mobile devices, ensuring high-performance inference operations with minimal size; pick ncnn if ncnn is a high-performance framework for deep learning inference on mobile platforms written in C++, supporting conversion from multiple DL frameworks via pnnx.
Markdown twin · FeatherCNN alternatives · ncnn alternatives
GraphCanon updated 2w
Trust & integrity
| Signal | FeatherCNN | ncnn |
|---|---|---|
| Maintenance | Dormant (2506d since push) As of 2w · github_public_v1 | Very active (0d since push) As of 2w · github_public_v1 |
| Provenance | Not a fork · Organization account As of 2w · github_public_v1 | Not a fork · Organization account As of 2w · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of 1mo · osv@v1 | No lockfile (source not queried) As of 1mo · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- FeatherCNN
- high-performance lightweight CNN inference library
- ncnn
- High-performance neural network inference framework optimized for mobile platforms
Stars
- FeatherCNN
- 1.2k
- ncnn
- 24k
Forks
- FeatherCNN
- 275
- ncnn
- 4.5k
Open issues
- FeatherCNN
- 20
- ncnn
- 1.2k
Language
- FeatherCNN
- C++
- ncnn
- C++
Adopt for
- FeatherCNN
- FeatherCNN is optimized for ARM CPUs and mobile devices, ensuring high-performance inference operations with minimal size.
- ncnn
- ncnn is a high-performance framework for deep learning inference on mobile platforms written in C++, supporting conversion from multiple DL frameworks via pnnx.
Persona
- FeatherCNN
- -
- ncnn
- -
Runtime
- FeatherCNN
- -
- ncnn
- -
License
- FeatherCNN
- -
- ncnn
- Other, details not specified within the provided repository content.
Last pushed
- FeatherCNN
- Sep 24, 2019
- ncnn
- Aug 4, 2026
Categories
- FeatherCNN
- Inference & Serving
- ncnn
- Inference & Serving
Trust and health
Maintenance
- FeatherCNN
- Dormant (18%)
- ncnn
- Very active (96%)
Days since push
- FeatherCNN
- 2506d
- ncnn
- 0d
Open issues (now)
- FeatherCNN
- 20
- ncnn
- 1.2k
Full report
- FeatherCNN
- Trust report
- ncnn
- Trust report
Choose FeatherCNN if…
- Tags unique to FeatherCNN: convolutional-neural-networks, inference-engine, ios.
- Targeting lightweight CNN inference on iOS or Android devices
- Leaner open-issue backlog (20).
When NOT to use FeatherCNN
- Inference needs are primarily for x86 architecture systems
- Project requires extensive third-party dependency support
Choose ncnn if…
- Requirements: Requires pnnx for exporting PyTorch models to ncnn..
- Tags unique to ncnn: artificial-intelligence, darknet, deep-learning, high-performance.
- For users requiring fast inference speeds optimized for mobile devices such as Android and iOS.
When NOT to use ncnn
- If working in an environment where GPU acceleration on desktop or server is more beneficial than CPU efficiency.
- For tasks that demand extensive training within the framework itself, as ncnn focuses on inference rather than training capabilities.
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (Tencent/FeatherCNN) · observed Aug 4, 2026
- GitHub forks (Tencent/FeatherCNN) · observed Aug 4, 2026
- Last push (Tencent/FeatherCNN) · observed Sep 24, 2019
- License file (unknown) · observed Aug 4, 2026
- Decision facts (enrichment) · observed Jul 16, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (Tencent/ncnn) · observed Aug 4, 2026
- GitHub forks (Tencent/ncnn) · observed Aug 4, 2026
- Last push (Tencent/ncnn) · observed Aug 4, 2026
- License file (Other) · observed Aug 4, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: FeatherCNN 1.2k · ncnn 24k (synced Aug 4, 2026).
Common questions
- What is the difference between FeatherCNN and ncnn?
- FeatherCNN: high-performance lightweight CNN inference library. ncnn: High-performance neural network inference framework optimized for mobile platforms. See the comparison table for live GitHub stats and shared categories.
- When should I choose FeatherCNN over ncnn?
- Choose FeatherCNN over ncnn when Tags unique to FeatherCNN: convolutional-neural-networks, inference-engine, ios; Targeting lightweight CNN inference on iOS or Android devices; Leaner open-issue backlog (20).
- When should I choose ncnn over FeatherCNN?
- Choose ncnn over FeatherCNN when Requirements: Requires pnnx for exporting PyTorch models to ncnn.; Tags unique to ncnn: artificial-intelligence, darknet, deep-learning, high-performance; For users requiring fast inference speeds optimized for mobile devices such as Android and iOS.
- When should I avoid FeatherCNN?
- Inference needs are primarily for x86 architecture systems Project requires extensive third-party dependency support
- When should I avoid ncnn?
- If working in an environment where GPU acceleration on desktop or server is more beneficial than CPU efficiency. For tasks that demand extensive training within the framework itself, as ncnn focuses on inference rather than training capabilities.
- Is FeatherCNN or ncnn more popular on GitHub?
- ncnn has more GitHub stars (23,644 vs 1,228). Stars measure visibility, not whether either tool fits your constraints.
- Are FeatherCNN and ncnn open source?
- Yes - both are open-source projects on GitHub.
- Where can I find alternatives to FeatherCNN or ncnn?
- GraphCanon lists graph-backed alternatives at FeatherCNN alternatives and ncnn alternatives (FeatherCNN markdown twin, ncnn markdown twin), ranked by typed relationship edges rather than popularity votes.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, FeatherCNN or ncnn?
- FeatherCNN: Dormant. ncnn: Very active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
- Where are the full trust reports for FeatherCNN and ncnn?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: FeatherCNN trust report; ncnn trust report.