NVIDIA-Nemotron-3.5-Transcribe-30B-A4B

Name: NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
Author: NVIDIA

NVIDIANVIDIAStatus: active

NVIDIA-Nemotron-3.5-Transcribe-30B-A4B is a general purpose, coding, multilingual AI model developed by NVIDIA. It was released on 2026-10-07. Its tracked lifecycle status is active. It has 30B parameters.

Specifications

Organization: NVIDIA
Model family: NVIDIA
Status: active
Released: 2026-10-07
Model type: General Purpose, Coding, Multilingual
Input modalities: text, audio
Output modalities: text
Parameters: 30B
Weights: unknown
Official API: No
Self-hostable: Yes
Last verified: 2026-11-02

Official sources

Hugging Face Hugging Face

Related models in the NVIDIA family

DeepSeek-V4.1-Flash-1017-NVFP4 2026-10-30 · active
MotionBricks 2026-10-23 · active
NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16 2026-10-16 · active
NVIDIA-Nemotron-Labs-Dory1.0-4B-GGUF 2026-10-16 · active
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 2026-10-12 · active
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 2026-10-12 · active
GLM-5.3-Flash-FP4-Local 2026-10-08 · active
Qwen3.8-Flash-Next-FP4-Local 2026-10-08 · active
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB 2026-10-07 · active
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-GGUF 2026-10-07 · active
NVIDIA-Nemotron-3.5-Bolt-E4B-4GB 2026-10-05 · active
PixelUMM 2026-10-01 · active

Interactive filtering and search on this page need JavaScript; every fact above is part of the page itself.