NVIDIA Open-Sources Nemotron 3.5 Transcribe, a 30B MoE Model

NVIDIA released Nemotron 3.5 Transcribe, an open-weight, promptable 30B MoE model (about 4B active parameters) that handles transcription across 40 languages in a single checkpoint, promoted as going beyond transcription.

2026-11-16 ~ 2026-11-18 · 2 related posts