What GPU do I need to run NbAiLab/nb-whisper-large?
1.5B parameters, published in F32. View on Hugging Face
Set up nb-whisper-largenb-whisper-large is published by NbAiLab on Hugging Face, with 13,181 downloads and 43 likes to date. It's a WhisperForConditionalGeneration model built for automatic-speech-recognition, published natively in F32.
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) |
|---|---|---|---|---|---|
| FP32 | 5.7 GB | 6.9 GB | Quadro M4000 | 1 | $0.058/hr |
| FP8 (quantized) | 1.4 GB | 1.7 GB | RTX 4000 SFF Ada | 1 | $0.198/hr |
| INT4 (quantized) | 0.7 GB | 0.9 GB | RTX 3060 | 1 | $0.110/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 nb-whisper-large at its published (F32) precision: 1× Quadro M4000, at $0.058/hr per GPU ($0.058/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
nb-whisper-large: common questions
Does nb-whisper-large fit on a 8 GB GPU?
Yes. At FP32 it needs 6.9 GB of VRAM, so an 8 GB card holds it with 1.1 GB to spare. A 6 GB card is not enough for it at FP32.
Can nb-whisper-large run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 5.7 GB, or 6.9 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 2.9 GB, or 3.4 GB with overhead. That moves it onto a 6 GB card instead of an 8 GB one. How much accuracy the cast costs is model-specific and is not measured here.
What is the least VRAM nb-whisper-large can run in?
0.9 GB, at INT4 (quantized), which fits a 6 GB card, against 6.9 GB at FP32. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Whisper models
- whisper-large-v3 (1.5B, F16)
- Whisper-Hindi2Hinglish-Prime (1.5B, F32)
- whisper-large-v3 (1.5B, F32)
- whisper-large-v3-german (1.5B, BF16)
- whisper-large-v3-russian (1.5B, BF16)
Lineage
Based on whisper-large.
Alternatives at this size
Other models for automatic-speech-recognition within about a third of nb-whisper-large's 1.5B parameters, from other model lines.
- parakeet-ctc-1.1b (1.1B, F32)
- cohere-transcribe-03-2026 (2.1B, BF16)
- seamless-m4t-v2-large (2.3B, F32)
- granite-speech-4.1-2b (2.3B, BF16)
- Qwen3-ASR-1.7B-hf (2.0B, BF16)
More on nb-whisper-large
Fits on an 8 GB GPU at FP32: every model that fits in 8 GB.
Related reading: H100 pricing and specs, Whisper variants compared, What AI inference is, and What AI model fine-tuning is.
