Skip to content
Local AI Wizard
Your machine
Theme

dots.mocr

dots studio · dots-studio/dots.mocr

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

Reported by the publisher30 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 updated2026-07-04A 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

30 results · dots studio's model card · read 2026-10-25
olmOCR-Bench
1,104.41.1 Elo Score of different bench between latest models
OmniDocBench (v1.5)
1,059.01.1 Elo Score of different bench between latest models
XDocParse
1,210.71.1 Elo Score of different bench between latest models
Average
1,124.71.1 Elo Score of different bench between latest models
ArXiv
85.91.2 olmOCR-bench
Old scans math
85.51.2 olmOCR-bench
Tables
90.71.2 olmOCR-bench
Old scans
48.21.2 olmOCR-bench
Every reported result30
Headers & footers
94.01.2 olmOCR-bench
Multi column
85.31.2 olmOCR-bench
Long tiny text
81.61.2 olmOCR-bench
Base
99.71.2 olmOCR-bench
Unisvg · Low-Level
0.8502. Structured Graphics Parsing
Unisvg · High-Level
0.9232. Structured Graphics Parsing
Unisvg · Score
0.8942. Structured Graphics Parsing
Chartmimic
0.7722. Structured Graphics Parsing
Design2Code
0.8012. Structured Graphics Parsing
Genexam
0.6642. Structured Graphics Parsing
SciGen
0.6602. Structured Graphics Parsing
ChemDraw
0.7902. Structured Graphics Parsing
CharXiv_descriptive
77.43. General Vision Tasks
CharXiv_reasoning
55.33. General Vision Tasks
OCR_Reasoning
22.853. General Vision Tasks
infovqa
73.763. General Vision Tasks
docvqa
91.853. General Vision Tasks
ChartQA
83.23. General Vision Tasks
OCRBench
86.03. General Vision Tasks
AI2D
82.163. General Vision Tasks
CountBenchQA
94.463. General Vision Tasks
refcoco
80.033. General Vision Tasks

Values as printed on the card, with the publisher's own settings (card section: Evaluation › 1. Document Parsing › 1.1 Elo Score of different bench between latest models; Evaluation › 1. Document Parsing › 1.2 olmOCR-bench); column “dots.mocr”. 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.mocr on 2026-03-19: 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_mocr

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

vLLM · model card · vLLM inference
CUDA_VISIBLE_DEVICES=0 vllm serve rednote-hilab/dots.mocr --tensor-parallel-size 1 --gpu-memory-utilization 0.9 --chat-template-content-format string --served-model-name model --trust-remote-code

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.mocr
Task
image-text-to-text
Architecture
DotsOCRForCausalLM
Library in source
dots_mocr
Weight license
MITdots-studio/dots.mocr 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.mocr README news (GitHub) · read 2026-10-18source
Every stored field12 fields
Revision checked
e539fbb52280393adc081b289ec597430a0f9031
Architecture
DotsOCRForCausalLM
Library
dots_mocr
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
2026-03-19creation is not the model's release
Repository updated
2026-07-04a commit is not a release date
Hub downloads (30 days) · likes
188,979 · 186this 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.