rknn-llm
Runs large language models on Rockchip NPU hardware using the RKNN runtime, letting you serve LLM inference locally on edge devices.
- •You have a Rockchip RK3588 (or similar) board and want to run LLM inference without cloud APIs.
- •Your product needs low‑latency AI responses on‑device (e.g., voice assistants, on‑edge chat).
- •You want to convert a Hugging‑Face model to RKNN format once and reuse it for many inferences.
python examples/chat.py --model llama3-8b.rknn --prompt "Act as a startup advisor and suggest three go‑to‑market strategies for a SaaS product that automates invoice processing."
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Installs with a command or two; your AI agent can do it for you.
mkdir -p ~/.claude/skills/rknn-llm && curl -fsSL https://workflowstacks.com/api/skills/rknn-llm/claude-skill -o ~/.claude/skills/rknn-llm/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
What's inside — free to inspect
Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Installs with a command or two; your AI agent can do it for you.
mkdir -p ~/.claude/skills/rknn-llm && curl -fsSL https://workflowstacks.com/api/skills/rknn-llm/claude-skill -o ~/.claude/skills/rknn-llm/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Are you the creator of this tool? and earn 85% of every sale.
Show it off in your README:
[](https://workflowstacks.com/skills/rknn-llm?utm_source=github&utm_medium=badge)The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.
Related skills
More ai-agent tools founders pair with this one.