Show HN: CPU First Decision Model

Category: ai-ml

Tags: decision-making, calibration, cpu-inference, llama-cpp, local-models

Score: 7.0/10 (Innovation: 7, Technical: 7, Documentation: 8, Utility: 6)

Gutsy is a fine-tuned 0.8B parameter model (based on Qwen3.5) that provides calibrated probabilities for decision-making questions instead of text generation. It runs efficiently on CPU via llama.cpp, offers a Jev-compatible inference API, and emphasizes privacy, determinism, and calibration for tasks like support triage, model routing, and fact checking.

Target audience: backend developers, ML engineers, devops

Repository: https://github.com/kouhxp/gutsy · HTML · Apache-2.0 · 94 stars

View on Hacker News