dots-studio / image-text-to-text updated 10 months ago

dots.ocr

dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model

Params
3.0 B
Context
131,072
Downloads 30d
831 K
Likes
1,331
Commercial use: allowed mit Not gated SAFETENSORS 3 languages View on Hugging Face ↗

Download history

tracking started — chart appears after 7 days of snapshots (1 recorded)
831 K downloads in the last 30 days

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 6.1 GB 7.6 GB ✅ Runs comfortably
model.safetensors (bf16, full) bf16 + 128K ctx 6.1 GB 14.5 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture
DotsOCRForCausalLM
Parameters
3.0 B
Tensor type
BF16
Context length
131,072
Vocabulary
151,936
Layers / heads
28 / 12
Licence
mit
First seen on the Hub
2025-07-30
Training datasets
undisclosed
Added to our catalog
2026-09-21
Compare with any image-text-to-text model