nvidia

Parakeet TDT 0.6B v3

NVIDIA's multilingual speech recognition model; card says audio up to 24 minutes on an A100 80GB with full attention, or 3 hours with local attention.automatic speech recognitioncc-by-4.0539.9K downloadsHugging Face

Cheapest GPU in stock that fits

A single GPU with at least 2.8 GB for inference.

NosanaIn stock · 6 freeStart right away

1× RTX 30608 GB VRAM

Nosana network, hosts worldwide

Details

Stock and price checked 17 min ago.

Self-service: you start it yourself, with no order or sales contact.

nvidia-3060

Full price

€0.04

per hour, whole instance, 1 GPU

View offer

GPU memory it needs

From model cards and vendor documentation. Lower precision needs less memory, with slightly lower quality. Estimates are marked.

What you want to do	Precision	Minimum	Basis
Run the model Arithmetic: 2.34 GiB fp32 weights x 1.2 runtime overhead. No VRAM figure published; card states at least 2 GB of RAM to load and more for longer audio.	FP32, full	2.8 GB	Estimated