Models · MarkTechPost ·
Meet Nemotron Labs 3 Puzzle 75B A9B: A Compressed Hybrid MoE LLM Delivering 2.03x Server Throughput
NVIDIA released Nemotron-Labs-3-Puzzle-75B-A9B, a compressed version of Nemotron-3-Super built with alternating structural compression and short distillation recovery phases. The model reduces parameters from 120.7B total/12.8B active to 75.3B/9.3B and is reported to deliver 2.03x throughput on a single 8xB200 node.