01

Basic information

Model repository: nv-community/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-DFlash2
Organization: nv-community
Tasks: Not provided

02

Architecture and runtime

Model type: qwen3
Architecture: DFlash2DraftModel
Libraries: safetensors
Base models: nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
Current revision: master

03

License and update history

License: openmdw-1.1
Created: 2026-10-27
Last updated: 2026-10-29

nvidianemotron-3.5speculative-decodingdflash2draft-modelspeechasrvllm
04

Hardware requirements

Not filled in locally.

05

Download links

Not filled in locally.

06

Basic usage example

Not filled in locally.