What GPU do I need to run dots-studio/dots.ocr?
3.0B parameters, published in BF16. View on Hugging Face
Set up dots.ocrdots.ocr is published by dots-studio on Hugging Face, with 290,679 downloads and 1,327 likes to date. It's a DotsOCRForCausalLM model built for image-text-to-text, 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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 5.7 GB | 6.8 GB | RTX 5060 Ti | 1 | $0.110/hr |
| FP8 (quantized) | 2.8 GB | 3.4 GB | RTX 5060 Ti | 1 | $0.110/hr |
| INT4 (quantized) | 1.4 GB | 1.7 GB | RTX 5060 Ti | 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 dots.ocr at its published (BF16) precision: 1× RTX 5060 Ti, at $0.110/hr per GPU ($0.110/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
dots.ocr: common questions
Does dots.ocr fit on a 8 GB GPU?
Yes. At BF16 it needs 6.8 GB of VRAM, so an 8 GB card holds it with 1.2 GB to spare. A 6 GB card is not enough for it at BF16.
How many copies of dots.ocr fit on one RTX 5060 Ti?
2, by VRAM alone. That card carries 16.0 GB and one copy needs 6.8 GB at BF16, on a live rate of $0.110/hr for the whole card. Throughput is not modelled here, so 2 copies is not 2 times the requests served.
What is the least VRAM dots.ocr can run in?
1.7 GB, at INT4 (quantized), which fits a 6 GB card, against 6.8 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More dots-studio models
- dots.mocr (3.0B, BF16)
Related reading: H100 pricing and specs, The best GPUs for AI, ranked, and Best GPU for LLM inference.
