NVIDIA Releases Nemotron-Labs-3-Puzzle-75B-A9B: A Compressed Hybrid MoE LLM Delivering 2.03x Server Throughput
On July 9, 2026, NVIDIA introduced the Nemotron-Labs-3-Puzzle-75B-A9B, a large language model (LLM) that features a compressed hybrid Mixture-of-Experts (MoE)...