DistillAgent-PaperQA-3B-GGUF

GGUF exports for QuantumCuddle/DistillAgent-PaperQA-3B.

Main HF model repo:

• https://huggingface.co/QuantumCuddle/DistillAgent-PaperQA-3B

Files:

• ...-F16.gguf (high quality, larger)
• ...-Q4_K_M.gguf (smaller/faster, if uploaded)

Example (llama.cpp):

llama-cli -m qwen-qwen25-3b-instruct-qasper-qasper_qwen25_3b_sft_v2_fixed-F16.gguf -p "QUESTION: ..."

For metrics, training details, and limitations, see the main model card.