NVIDIA Nemotron 3.5 Transcribe 30B A4B
NVIDIA Nemotron-3.5-Transcribe is an offline speech and audio model that processes recordings, together with text instructions and optional context, into text responses.
NVIDIA Nemotron 3.5 Transcribe 30B A4B launched on 7 October 2026. It ranked #15 on Daily Launch on 30 October 2026 with a Launch Score of 66, from trending score 408 on Hugging Face. It moved up 34 places from the day before.
What is NVIDIA Nemotron 3.5 Transcribe 30B A4B?
Nemotron 3.5 Transcribe is an open-weight, offline speech and audio model for transcription in 40 languages, with support for recordings up to one hour and a 65,536-token context. Its hybrid mixture-of-experts architecture activates approximately 4.3B parameters, including the audio encoder, and it is released in BF16, FP8, and NVFP4 precision.
From its model card on Hugging Face
NVIDIA Nemotron 3.5 Transcribe 30B A4B is a model by nvidia on Hugging Face. It is released under the openmdw-1.1 license.
How to get NVIDIA Nemotron 3.5 Transcribe 30B A4B
pip install git+https://github.com/huggingface/transformersFrom its model card on Hugging Face
More steps and the source are in its model card on Hugging Face.