Skip to content
Local AI Wizard
Your machine
Theme

dots.ocr

dots studio · dots-studio/dots.ocr

Weights license: MIT · code and components may use other terms

Reported by the publisher14 resultsdots studio's model card · read 2026-10-25 · not ranked · see them
Memory needed~3 GBQ4 weights + working room, before the machine's reserve
Parameters3 BHub safetensors total
Repository updated2025-10-31A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

14 results · dots studio's model card · read 2026-10-25
Overall Edit ↓
0.177The end-to-end evaluation results of different tasks.
Text Edit ↓
0.075The end-to-end evaluation results of different tasks.
Formula Edit ↓
0.297The end-to-end evaluation results of different tasks.
Table TEDS ↑
79.2The end-to-end evaluation results of different tasks.
Table Edit ↓
0.186The end-to-end evaluation results of different tasks.
Read Order Edit ↓
0.152The end-to-end evaluation results of different tasks.
ArXiv
82.13. olmOCR-bench.
Old Scans Math
64.23. olmOCR-bench.
Every reported result14
Tables
88.33. olmOCR-bench.
Old Scans
40.93. olmOCR-bench.
Headers and Footers
94.13. olmOCR-bench.
Multi column
82.43. olmOCR-bench.
Long Tiny Text
81.23. olmOCR-bench.
Base
99.53. olmOCR-bench.

Values as printed on the card, with the publisher's own settings (card section: Benchmark Results › 2. dots.ocr-bench › The end-to-end evaluation results of different tasks.; Benchmark Results › 3. olmOCR-bench.); column “dots.ocr”. Not comparable across publishers and not used in any ranking. Model card

Runs on

Fast memory holds it 118

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 118

Within memory, outside the fast part 1

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Consider it for

dots studio released dots.ocr on 2025-07-30: a vision-language model that answers about images, with 3.04B parameters on the Hugging Face count and the MIT license. Languages the publisher declares: en, zh.

Check first

License: commercial use allowed. At Q4 the weights load about 2.3 GB before each machine's reserve; image resolution, video frames and context add memory, and the vision encoder needs support in the runtime you pick.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: dots_ocr

Documented ways to run it

The card's code needs paths it does not give

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / source
dots-studio/dots.ocr
Task
image-text-to-text
Architecture
DotsOCRForCausalLM
Library in source
dots_ocr
Weight license
MITdots-studio/dots.ocr model card (Hugging Face) · read 2026-10-18source
Commercial use
Allowed MIT license text (SPDX) · read 2026-10-18license text
Languages
en, zhModel card metadata · read 2026-10-25source
Released
dots.ocr model card News (Hugging Face) · read 2026-10-18source
Every stored field12 fields
Revision checked
c0111ce6bc07803dbc267932ffef0ae3a51dc951
Architecture
DotsOCRForCausalLM
Library
dots_ocr
Hub task tag
image-text-to-text
Formats
safetensors, transformers
Access
Open download
Publisher kind
Official
Hub parameter count
3,039,179,264safetensors.total
Repository created
2025-07-30creation is not the model's release
Repository updated
2025-10-31a commit is not a release date
Hub downloads (30 days) · likes
504,913 · 1,344this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Curated facts checked: 2026-10-18. The license and release date cite the publisher's sources; parameters, files and task come from the Hugging Face record, and memory is a labelled estimate from its parameter count. A value no source states stays empty; a repository commit is not a model release date.