yassa9/qwen600

Static suckless single batch CUDA-only qwen3-0.6B mini inference engine

43
/ 100
Emerging

This is a specialized tool for developers working with large language models. It provides a highly optimized, minimalist inference engine for the Qwen3-0.6B instruct model, allowing developers to run this specific model on their NVIDIA GPUs. It takes the model's weights and a prompt as input and outputs generated text, often faster than other solutions, making it ideal for those who need to integrate this model into custom applications.

546 stars. No commits in the last 6 months.

Use this if you are a developer seeking a very fast, low-dependency way to run the Qwen3-0.6B LLM on an NVIDIA GPU for integration into your own C/C++ projects.

Not ideal if you are looking for a general-purpose LLM interface, support for various models, or a Python-centric development environment.

LLM-development GPU-programming AI-inference systems-programming embedded-AI
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 16 / 25

How are scores calculated?

Stars

546

Forks

48

Language

Cuda

License

MIT

Last pushed

Sep 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/yassa9/qwen600"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.