AIMarkTechPostabout 1 hour ago
NVIDIA Releases Compressed Hybrid MoE LLM
10 min read
NVIDIA released Nemotron-Labs-3-Puzzle-75B-A9B, a compressed variant of Nemotron-3-Super. The compressed model has 75.3B total and 9.3B active parameters, down from 120.7B total and 12.8B active. It delivers 2.03x server throughput at 100 tokens per second per user with 8 concurrent users.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyNvidia
