What GPU do I need to run bigscience/bloomz-560m?
559M parameters, published in F16. View on Hugging Face
Set up bloomz-560mbloomz-560m is published by bigscience on Hugging Face, with 974,467 downloads and 138 likes to date. It's a BloomForCausalLM model built for text-generation, published natively in F16.
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 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run bloomz-560m at its published (F16) precision: 1× RTX 3070 on simplepod, at $0.050/hr per GPU ($0.050/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
bloomz-560m: common questions
How much VRAM does bloomz-560m need?
1.2 GB at FP16, 0.6 GB at FP8 (quantized), 0.3 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 1.0 GB of weights plus inference overhead is the whole requirement.
How many copies of bloomz-560m fit on one RTX 3070?
6, by VRAM alone. That card carries 8.0 GB and one copy needs 1.2 GB at FP16, on a live rate of $0.050/hr for the whole card. Throughput is not modelled here, so 6 copies is not 6 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More bigscience models
- bloom-560m (559M, F16)
- bloom-1b7 (1.7B, F16)
- bloom-3b (3.0B, F16)
- bloom (176.2B, BF16)
- bloom-1b1 (1.1B, F16)
- bert-base-uncased (110M, F32)
