#165 · Primary category： Inference & Local Deploy
timber
Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference code. One command to load, one command to serve. 336x faster than Python inference.
Project last updated：04/16/26
GitHub Stars
687
Forks
23
Contributors
2
License
Apache-2.0
Why we included this project
Timber takes trained classical models and compiles them down to a self-contained C99 binary, so you can drop the Python runtime from the serving path entirely. The result is a tiny artifact, around 48 KB, that runs single-sample inference in about two microseconds, which is what makes it interesting for teams doing real-time transaction scoring or running on constrained edge hardware. It also ships an Ollama-compatible HTTP server, so one command loads a model and another serves it. The acceleration backend can emit SIMD, GPU, FPGA, or embedded variants, meaning the same model can move from a server to a microcontroller without reworking the pipeline. For regulated environments that want deterministic, auditable inference, that portability plus the lack of runtime dependencies is a real selling point.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.