What GPU do I need to run microsoft/VibeVoice-ASR?
8.7B parameters, published in BF16. View on Hugging Face
VibeVoice-ASR is published by microsoft on Hugging Face, with 697,553 downloads and 1,276 likes to date. It's a VibeVoiceForASRTraining 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.
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 caveat: requires a quantized checkpoint actually published for this model — check its Hugging Face page before relying on this row.
Cheapest way to run VibeVoice-ASR at its published (BF16) precision: 1× RTX 3090 on simplepod, at $0.160/hr per GPU ($0.160/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More microsoft models
- Florence-2-base (232M, F16)
- phi-2 (2.8B, F16)
- Phi-3.5-vision-instruct (4.1B, BF16)
- Phi-3.5-mini-instruct (3.8B, BF16)
- phi-4 (14.7B, BF16)
- Phi-3-mini-4k-instruct (3.8B, BF16)
