NotPunchnox / rkllama
Ollama alternative for Rockchip NPU: An efficient solution for running AI and Deep learning models on Rockchip devices with optimized NPU support ( rkllm )
Why this job: matched by what the repo talks about: model, device, ollama, optimiz
What it does
- Running models on NPU.
- Ollama API compatibility. Support for:
- Partial OpenAI API compatibility. Support for:
- Tool/Function Calling. Complete support for tool calls with multiple LLM formats (Qwen, Llama 3.2+, others).
- Pull models directly from Huggingface.
Get started
git clone https://github.com/notpunchnox/rkllama
cd rkllama - Maintenance
- Active
- Last commit 15 days ago
- Stars
- 626
- +8 this week
- Licence
- GPL-3.0
- Share-alike terms
- Downloads for
- None listed
- No release files
- Latest tag
- Release
- Released 19 months ago
- Built with
- Python
- 98% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- 34% closed
- 63 still open
- Pull requests
- 69 merged
- 5 waiting
- Releases
- 3
- 0 in the last year
- No contributing guide
- No security policy
- No code of conduct
More: languages, topics and project record
Languages
- Python 98%
- Shell 1%
- Dockerfile <1%
Topics
- ai
- client-server
- ia
- llm
- npu
- offline
- orangepi
- orangepi5
- orangepi5pro
- python
- rk3576
- rk3588
Project record
- JobLocal LLMs
- StatusListed
- Commits377
- Forks105
- Watching22
- Stars in 28 days+11
- CreatedDec 30, 2024
- First seen by usNov 7, 2026
- CheckedNov 12, 2026