What GPU do I need to run ibm-granite/granite-speech-3.2-8b?
8.5B parameters, published in BF16. View on Hugging Face
granite-speech-3.2-8b is published by ibm-granite on Hugging Face, with 62,584 downloads and 88 likes to date. It's a GraniteSpeechForConditionalGeneration 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 granite-speech-3.2-8b 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 ibm-granite models
- granite-4.1-8b (8.8B, BF16)
- granite-4.1-30b (28.9B, BF16)
- granite-speech-4.1-2b (2.3B, BF16)
- granite-guardian-3.3-8b (8.2B, BF16)
- granite-docling-258M (258M, BF16)
- granite-4.1-3b (3.4B, BF16)
