plushpluto/kllm
Welcome to KLLM, an advanced project focused on core kernel AI development, integrating on-device language models (LMs) for efficient and powerful AI capabilities.
KLLM helps device manufacturers, mobile OS developers, and AI application developers integrate powerful language models directly into their devices and operating systems. It allows for on-device processing of AI tasks, taking in user commands or sensor data and producing intelligent responses or actions, all while prioritizing user privacy and system efficiency.
No commits in the last 6 months.
Use this if you are developing operating systems, smart devices, or AI applications where privacy, offline capability, energy efficiency, and low latency are critical.
Not ideal if your application strictly requires massive cloud-based language models or if your primary users are cloud infrastructure engineers.
Stars
8
Forks
1
Language
C++
License
MIT
Category
Last pushed
Oct 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/plushpluto/kllm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
thu-pacman/chitu
High-performance inference framework for large language models, focusing on efficiency,...
sophgo/LLM-TPU
Run generative AI models in sophgo BM1684X/BM1688
NotPunchnox/rkllama
Ollama alternative for Rockchip NPU: An efficient solution for running AI and Deep learning...
Deep-Spark/DeepSparkHub
DeepSparkHub selects hundreds of application algorithms and models, covering various fields of...
howard-hou/VisualRWKV
VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle...