Model · multimodal model
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B is a multimodal model from NVIDIA, first covered on 28 October 2026. It is available as open weights you can download and run (licence: OpenMDW-1.1). Its context window is 65,536 tokens.
Last updated
Quick facts
- Who makes NVIDIA-Nemotron-3.5-Transcribe-30B-A4B?
- NVIDIA-Nemotron-3.5-Transcribe-30B-A4B is made by NVIDIA. NVIDIA news →
- When was NVIDIA-Nemotron-3.5-Transcribe-30B-A4B released?
- The first report of NVIDIA-Nemotron-3.5-Transcribe-30B-A4B's release that Digest AI covered was published on 28 October 2026.
- What type of model is NVIDIA-Nemotron-3.5-Transcribe-30B-A4B?
- NVIDIA-Nemotron-3.5-Transcribe-30B-A4B is a multimodal model.
- Are NVIDIA-Nemotron-3.5-Transcribe-30B-A4B's weights open?
- Yes. NVIDIA-Nemotron-3.5-Transcribe-30B-A4B is released as open weights that can be downloaded and run, under the OpenMDW-1.1 licence.
- What is NVIDIA-Nemotron-3.5-Transcribe-30B-A4B's context window?
- NVIDIA-Nemotron-3.5-Transcribe-30B-A4B's context window is 65,536 tokens.
- Where is NVIDIA-Nemotron-3.5-Transcribe-30B-A4B available?
- NVIDIA-Nemotron-3.5-Transcribe-30B-A4B is available as open weights that can be downloaded and run. huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcri ↗
Taken from the coverage, not from our own testing. A question is left out when none of the reports we read gave the answer. All tracked models →
1 story about NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
-
NVIDIA releases open-weight Nemotron 3.5 Transcribe model and Granary v2 dataset
NVIDIA has released Nemotron 3.5 Transcribe, an open-weight speech model that combines multilingual transcription, speaker attribution, translation, and audio question answering in a single checkpoint. The model…
12 sources primary source HN 124AWS Machine Learning BlogMarkTechPostnote.comThe Decoder +7 more
Other models from NVIDIA