MNN and xllm

These are competitors—both are inference engines optimizing LLM execution on hardware accelerators, targeting the same use case of efficient on-device model deployment, though MNN has achieved significantly wider adoption and maturity.

MNN
93
Verified
xllm
72
Verified
Maintenance 25/25
Adoption 20/25
Maturity 25/25
Community 23/25
Maintenance 25/25
Adoption 10/25
Maturity 15/25
Community 22/25
Stars: 14,526
Forks: 2,234
Downloads: 220,239
Commits (30d): 77
Language: C++
License: Apache-2.0
Stars: 1,081
Forks: 149
Downloads:
Commits (30d): 136
Language: C++
License:
No risk flags
No Package No Dependents

About MNN

alibaba/MNN

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

Supports inference and training across multiple frameworks (TensorFlow, Caffe, ONNX, TorchScript) with specialized runtimes for LLMs via MNN-LLM and diffusion models via MNN-Diffusion. Employs aggressive optimization strategies including FP16/Int8 quantization (50-70% size reduction), minimal dependencies, and platform-specific backends to achieve sub-2MB executable overhead on iOS and 800KB core library on Android. Integrates with MNN Workbench for model visualization and one-click deployment across mobile, embedded, and IoT devices.

About xllm

jd-opensource/xllm

A high-performance inference engine for LLMs, optimized for diverse AI accelerators.

Scores updated daily from GitHub, PyPI, and npm data. How scores work