What GPU do I need to run NbAiLab/nb-asr-beta-qwen06b-lunde05?
782M parameters, published in BF16. View on Hugging FaceGated
nb-asr-beta-qwen06b-lunde05 is published by NbAiLab on Hugging Face, with 12,639 downloads and 0 likes to date. It's a Qwen3ASRForConditionalGeneration model built for automatic-speech-recognition, published natively in BF16, and gated: you'll need to accept the model's terms on Hugging Face before downloading weights.
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 | 1.5 GB | 1.7 GB | RTX 3070 | 1 | $0.088/hr |
| FP8 (quantized) | 0.7 GB | 0.9 GB | RTX 5060 Ti | 1 | $0.180/hr |
| INT4 (quantized) | 0.4 GB | 0.4 GB | RTX 3070 | 1 | $0.088/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-asr-beta-qwen06b-lunde05 at its published (BF16) precision: 1× RTX 3070, at $0.088/hr per GPU ($0.088/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
nb-asr-beta-qwen06b-lunde05: common questions
How much VRAM does nb-asr-beta-qwen06b-lunde05 need?
1.7 GB at BF16, 0.9 GB at FP8 (quantized), 0.4 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 1.5 GB of weights plus inference overhead is the whole requirement.
Do I need approval to download nb-asr-beta-qwen06b-lunde05?
Yes. NbAiLab gates this repository on Hugging Face, so you have to accept its terms with a signed-in account before the weights will download. It does not change the 1.7 GB the model needs once you have them.
How many copies of nb-asr-beta-qwen06b-lunde05 fit on one RTX 3070?
4, by VRAM alone. That card carries 8.0 GB and one copy needs 1.7 GB at BF16, on a live rate of $0.088/hr for the whole card. Throughput is not modelled here, so 4 copies is not 4 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
Alternatives at this size
Other models for automatic-speech-recognition within about a third of nb-asr-beta-qwen06b-lunde05's 782M parameters, from other model lines.
- whisper-large-v3-turbo (809M, F16)
- parakeet-ctc-1.1b (1.1B, F32)
- Qwen3-ASR-0.6B (938M, BF16)
- nemotron-3.5-asr-streaming-0.6b (638M, F32)
- distil-large-v3 (756M, F16)
More on nb-asr-beta-qwen06b-lunde05
Fits on an 8 GB GPU at BF16: every model that fits in 8 GB.
Best speech-to-text models: how nb-asr-beta-qwen06b-lunde05 ranks against the rest.
Related reading: RTX 3070 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