nvidia

Nemotron 3.5 Transcribe 30B

NVIDIA's speech transcription model, handling recordings up to 1 hour with word timestamps.automatic speech recognitionother70K downloadsHugging Face

Cheapest GPU in stock that fits

A single GPU with at least 80 GB for inference.

NosanaIn stock · 21 freeStart right away

Nosana network, hosts worldwide

Details

Stock and price checked 17 min ago.

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

Confidential computing: data stays encrypted while the GPU works on it, so the host can't read it.

nvidia-pro-6000-cc

Full price

€2.09

per hour, whole instance, 1 GPU

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	Setup	Basis
Run the model Model card's deployment target and vLLM example; a validated setup, not a stated hard minimum.	BF16, full	80 GB	1x H100 80 GB (per model card)	Published
Run the model Model card hardware table lists L40S PCIe 48GB with FP8; a validated setup, not a stated hard minimum.	FP8, 8-bit	48 GB	1x L40S 48GB (per model card)	Published
Run the model Model card hardware table lists RTX 5090 (32 GB) with NVFP4; a validated setup, not a stated hard minimum.	4-bit	32 GB	1x RTX 5090 (per model card)	Published