michelangeloromerochisco/ternative

Inference engine for ternary-weight LLMs with runtime LoRA - the llama.cpp of BitNet models

3 best points · 1 comments · 1 Hacker News post · 8 GitHub stars · View on GitHub

Hacker News discussions

• Ternative – C++/CUDA inference engine for ternary LLMs with runtime LoRA (3 points, 1 comments, by michelangeloro, 2026-05-19)