NVIDIA releases Puzzle-75B-A9B, a compressed Nemotron model with 2x throughput

NVIDIA has released the Nemotron-Labs-3-Puzzle-75B-A9B model, a deployment-optimized large language model derived from Nemotron-3-Super-120B-A12B. It utilizes the Iterative Puzzle post-training compression framework to significantly improve inference efficiency for reasoning-heavy and long-context workloads while maintaining strong downstream accuracy.

• Reduces parameters from 120.7B total / 12.8B active to 75.3B total / 9.3B active.
• Achieves approximately 2x higher server throughput on a single 8x B200 node at matched user-throughput constraints.
• Increases sustainable 1M-token single-H100 concurrency from 1 request to 8 requests.
• Maintains strong accuracy across reasoning, coding, multilingual, long-context, and agentic benchmarks.

The model supports Multi-Token Prediction for faster text generation and is ready for commercial use in English, French, German, Italian, Japanese, Spanish, and Chinese.