What GPU do I need to run microsoft/Florence-2-base?
232M parameters, published in F16. View on Hugging Face
Set up Florence-2-baseFlorence-2-base is published by microsoft on Hugging Face, with 2,752,500 downloads and 396 likes to date. It's a Florence2ForConditionalGeneration model built for image-text-to-text, 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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP16 | 0.4 GB | 0.5 GB | Quadro M4000 | 1 | $0.058/hr |
| FP8 (quantized) | 0.2 GB | 0.3 GB | RTX 4000 SFF Ada | 1 | $0.198/hr |
| INT4 (quantized) | 0.1 GB | 0.1 GB | RTX 3060 | 1 | $0.110/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 Florence-2-base at its published (F16) precision: 1× Quadro M4000, at $0.058/hr per GPU ($0.058/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Florence-2-base: 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.
KV-cache size for Florence-2-base is not published for this architecture, so no figure is shown.
Florence-2-base: common questions
How much VRAM does Florence-2-base need?
0.5 GB at FP16, 0.3 GB at FP8 (quantized), 0.1 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 0.4 GB of weights plus inference overhead is the whole requirement.
How many copies of Florence-2-base fit on one Quadro M4000?
15, by VRAM alone. That card carries 8.0 GB and one copy needs 0.5 GB at FP16, on a live rate of $0.058/hr for the whole card. Throughput is not modelled here, so 15 copies is not 15 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Florence-2 models
- Florence-2-base-ft (232M, F16)
- Florence-2-VQAJP2 (271M, BF16)
- Florence-2-large (777M, F16)
- Florence-2-large (777M, F16)
Alternatives at this size
Other models for image-text-to-text within about a third of Florence-2-base's 232M parameters, from other model lines.
- SmolVLM-256M-Instruct (256M, BF16)
- granite-docling-258M (258M, BF16)
More on Florence-2-base
Fits on an 8 GB GPU at FP16: every model that fits in 8 GB.
Best vision-language models: how Florence-2-base ranks against the rest.
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.
