Ternary Nemotron 30B-A3B runs on 12 GB GPU with 368K context in GGUF; supports Stock llama.cpp and PrismML fork/Bonsai

Ternary Nemotron 30B-A3B — 368K Context on 12 GB GPU (GGUF) A ternary (1.58-bit) 30B-A3B MoE model that runs on a 12 GB GPU with 368K context, 172 tok/s decode and 7000+ tok/s prefill — in both Stock llama.cpp and...