What GPU do I need to run bigscience/bloom-560m?

559M parameters, published in F16. View on Hugging Face

559M
Parameters
F16
Native precision
BloomForCausalLM
Architecture
text-generation
Pipeline

bloom-560m is published by bigscience on Hugging Face, with 467,931 downloads and 375 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 times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP161.0 GB1.2 GBQuadro M40001$0.046/hr
FP8 (quantized)0.5 GB0.6 GBRTX 5060 Ti1$0.180/hr
INT4 (quantized)0.3 GB0.3 GBRTX 30701$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 bloom-560m at its published (F16) precision: 1× Quadro M4000, at $0.046/hr per GPU ($0.046/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.

bloom-560m: KV cache by context length

The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.

Multi-head attention: every layer caches keys and values for every head. Cached per token: 98,304 bytes at 16-bit.

The model's maximum context length is not published in its configuration, so no per-context figures are shown.

Computed from the layer, head and window counts in the model's own configuration (bigscience/bloom-560m), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.

bloom-560m: common questions

How much VRAM does bloom-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 bloom-560m fit on one Quadro M4000?

6, by VRAM alone. That card carries 8.0 GB and one copy needs 1.2 GB at FP16, on a live rate of $0.046/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 BLOOM models

All 6 BLOOM models: VRAM and GPU requirements

Alternatives at this size

Other models for text-generation within about a third of bloom-560m's 559M parameters, from other model lines.

More on bloom-560m

Related reading: H100 pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.

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

Connect your accounts

One console for the GPU clouds you already use.

Connect your accounts for $20 a month, flat. Your provider bills the GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.