Deploying ONNX models from the catalog is coming soon. Today, download the files from Hugging Face and upload them in Inference.
Questions
How much GPU memory does Step-Audio-2-mini need?
About 1 GB: 0.03 GB of weights and the runtime's own memory.
What is the cheapest GPU to run Step-Audio-2-mini?
Right now one GTX 1080 at $0.07 an hour; RTX 5060 Ti at $0.15 an hour is the best value for its speed. Prices are live offers from GPU clouds, checked every 15 minutes.
Can Step-Audio-2-mini run on an RTX 4090?
Yes: it needs about 1 GB and an RTX 4090 has 24 GB.
Prices are per hour for the whole machine and its disk, right now. Speed is Vast's DLPerf score of the machine, relative to the cheapest. Best value: the most speed per dollar. Only machines with a Vast reliability above 95% that download at 400 Mbit/s or more are offered: the machine fetches the model itself.