Articles by tag: moe

NVIDIA Nemotron 3 Nano Omni: multimodal AI 9 times more efficient

NVIDIA introduced the open model Nemotron 3 Nano Omni, combining video, audio, and text. Learn about the 9x efficiency gain and architecture for enterprise AI agents.

Running MoE GPT-OSS-120B on 6 GB GPU up to 30 t/s

Accelerating GPT-OSS-120B on a weak GPU with -cmoe and --fit. Efficient RAM usage for MoE models. Instructions for developers.