Models

AI tuned for your field

Open AI models built for one job each, like patents, security, law, money, and health. Download and run them in private, right on your own computer.

The technical details
All weights are open. The two Patent Strategist builds start from DeepSeek-R1-0528-Qwen3-8B, are made with the NeMo toolkit, and ship two ways: GGUF files (ready to run with llama.cpp) and LoRA adapters (small training patches in BF16). On Spark-class hardware (a small ~$3,000 AI desktop) the Q5_K_M GGUF runs around 32 to 35 tokens per second. SecurityLLM builds on ZySec-AI/SecurityLLM, Saul 7B on Equall/Saul-7B-Instruct-v1, Finance Chat on AdaptLLM/finance-chat, and II-Medical 8B on Intelligent-Internet/II-Medical-8B, each shipped as GGUF from Q4 through Q8 and F16, and scored on domain tests like CyberMetric, LegalBench, FinanceBench, and MedMCQA. The Patent Strategist Bench is 200 questions across seven shapes (claim drafting, prior-art ranking, MPEP-grounded reasoning, and more), released CC-BY-4.0.