This model was converted to GGUF format from rstar2-reproduce/rStar2-Agent-14B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with Llamafile :)

Portable and fast...

bash

wget "https://github.com/Mozilla-Ocho/llamafile/releases/download/0.9.3/llamafile-0.9.3"
chmod +x llamafile-0.9.3
wget "https://huggingface.co/F-urkan/rStar2-Agent-14B-Q4_0-GGUF/resolve/main/rstar2-agent-14b-q4_0.gguf"
./llamafile-0.9.3 --server --port 8081 --no-mmap --nobrowser -ngl 9999 -m rstar2-agent-14b-q4_0.gguf

Requirements:

8 gb vram
8 gb disk space

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

bash

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo F-urkan/rStar2-Agent-14B-Q4_0-GGUF --hf-file rstar2-agent-14b-q4_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo F-urkan/rStar2-Agent-14B-Q4_0-GGUF --hf-file rstar2-agent-14b-q4_0.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo F-urkan/rStar2-Agent-14B-Q4_0-GGUF --hf-file rstar2-agent-14b-q4_0.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo F-urkan/rStar2-Agent-14B-Q4_0-GGUF --hf-file rstar2-agent-14b-q4_0.gguf -c 2048

License

MIT

Citation

bibtex

@misc{shang2025rstar2agent,
      title={rStar2-Agent: Agentic Reasoning Technical Report}, 
      author={Ning Shang and Yifei Liu and Yi Zhu and Li Lyna Zhang and Weijiang Xu and Xinyu Guan and Buze Zhang and Bingcheng Dong and Xudong Zhou and Bowen Zhang and Ying Xin and Ziming Miao and Scarlett Li and Fan Yang and Mao Yang},
      year={2025},
      eprint={2508.20722},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2508.20722}, 
}