What GPU do I need to run bigscience/bloom?
176.2B parameters, published in BF16. View on Hugging Face
bloom is published by bigscience on Hugging Face, with 17,704 downloads and 5,041 likes to date. It's a BloomForCausalLM model built for text-generation, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. 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 bloom at its published (BF16) precision: 5× A100 on runpod, at $1.19/hr per GPU ($5.95/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 bigscience models
- bloomz-560m (559M, F16)
- bloom-560m (559M, F16)
- bloom-1b7 (1.7B, F16)
- bloom-3b (3.0B, F16)
- bloom-1b1 (1.1B, F16)
- Qwen3-0.6B (752M, BF16)
