NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-ROCmFPX
- Task
- Speech recognition
- Category
- Audio
- License
- Custom (other)
- Commercial use
- Check the license
The license isn't a standard one; read the model card on Hugging Face before using it commercially. - Size
- About 30 billion parameters
- Memory to load
- ~18 GB (estimate)
- Format
- GGUF
- Runs on
- CPU
- Access
- Open download
- Downloads (last 30 days)
- 0
- Likes
- 0
- Last updated
- October 30, 2026
How to run it
This is a GGUF build, the format llama.cpp uses. It runs locally on a CPU or GPU with llama.cpp, Ollama or LM Studio, which load GGUF files directly.
Plan for roughly 18 GB of memory to load it (our estimate from its size and format).
The model card on Hugging Face has the exact usage code.
Where to run it
In the cloud
Needs about 18 GB: a 24 GB GPU such as an RTX 4090 or RTX A5000 is enough.
- RunPod · rent a GPU by the hour (affiliate link)
Related speech recognition models
Data from Hugging Face's public API, last checked October 30, 2026. Downloads are Hugging Face's count for the last 30 days.