What GPU do I need to run nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B?
33.7B parameters, published in BF16. View on Hugging Face
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B is published by nvidia on Hugging Face, with 69,992 downloads and 3,118 likes to date. It's a Nemotron3_5TranscribeForConditionalGeneration model built for automatic-speech-recognition, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for activations and allocator fragmentation. Speech models don't build the same growing KV-cache a text model does. Memory scales primarily with input audio length. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 62.8 GB | 75.3 GB | A100 | 1 | $1.31/hr |
| cheaper alt. | RTX A5000 | 4 | $0.704/hr | ||
| FP8 (quantized) | 31.4 GB | 37.7 GB | L40 | 1 | $0.759/hr |
| cheaper alt. | RTX 4000 Ada | 2 | $0.440/hr | ||
| INT4 (quantized) | 15.7 GB | 18.8 GB | RTX A5000 | 1 | $0.176/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run NVIDIA-Nemotron-3.5-Transcribe-30B-A4B at its published (BF16) precision: 1× A100, at $1.31/hr per GPU ($1.31/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B: common questions
Can NVIDIA-Nemotron-3.5-Transcribe-30B-A4B run on a single GPU?
Yes, but not on a desktop card. At BF16 it needs 75.3 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 80.0 GB A100 at $1.31/hr.
What is the least VRAM NVIDIA-Nemotron-3.5-Transcribe-30B-A4B can run in?
18.8 GB, at INT4 (quantized), which fits a 24 GB card, against 75.3 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing NVIDIA-Nemotron-3.5-Transcribe-30B-A4B lower the GPU bill?
Yes. At BF16 the cheapest live fit is one A100 at $1.31/hr. At INT4 (quantized) it drops to one RTX A5000 at $0.176/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Nemotron 3 models
- NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 (31.6B, F8_E4M3)
- NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 (31.6B, BF16)
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 (31.6B, BF16)
- NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16 (31.6B, BF16)
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16 (31.6B, BF16)
Lineage
Alternatives at this size
Other models for automatic-speech-recognition within about a third of NVIDIA-Nemotron-3.5-Transcribe-30B-A4B's 33.7B parameters, from other model lines.
- SOV-Transcribe-1 (26.6B, BF16)
More on NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
Fits on an 80 GB GPU at BF16: every model that fits in 80 GB.
Fits on a 48 GB GPU at FP8: every model that fits in 48 GB.
Fits on a 24 GB GPU at INT4: every model that fits in 24 GB.
Best speech-to-text models: how NVIDIA-Nemotron-3.5-Transcribe-30B-A4B ranks against the rest.
Related reading: A100 pricing and specs, Whisper variants compared, and What AI inference is.
Your own GPU cloud accounts
One console for the GPU clouds you already rent from. Your keys stay on your machine.
$20 a month, flat