Quantized GGUF build of hungrynovalabs/nova-pup-4b, a 4B-parameter Linux systems specialist and multi-agent problem solver. See the main repo for the full model card, benchmarks, and limitations.

Run it

With Ollama (or use the curated build: ollama run hungrynovalabs/nova-pup:4b):

ollama run hf.co/hungrynovalabs/nova-pup-4b-GGUF

With llama.cpp:

llama-cli -m nova-pup-4b.Q8_0.gguf -cnv

Training data & licensing

Nova Pup was trained using lawfully acquired technical materials and publicly available Linux documentation. Openly licensed materials retain their respective licenses. Copyrighted materials were used only for intermediate model training and are not distributed with the model.

Base model: InternScience Agents-A1-4B (Apache-2.0). Quantization: Q8_0. Based on Qwen3.5-4B (Apache 2.0) by the Qwen Team.