Models/jina ocr v1

Text / jinaai

jina ocr v1

jina-ocr-v1 is an end-to-end document parsing model built on DeepSeek-OCR, using a DeepEncoder vision tower and a 3B-parameter mixture-of-experts decoder with about 570M active parameters per token. It includes a FastMTP speculative decoding head. The repository includes model weights and custom code for loading. Reported scores include 91.14 overall on OmniDocBench v1.6 and 83.4 overall on olmOCR-Bench. It is licensed cc-by-nc-4.0, tagged multilingual, and supports an image-text-to-text pipeline.

EstimatedRepository opened Sep 1, 2026Source checked 9/24/2026Version: 904f815d

LOCALRENTED GPUOPEN WEIGHTS

Freshness 77 out of 100. Repository age: 68 days old, Sep 1, 2026. Measures age, not quality.

Popularity 46 out of 100. 1,738 downloads in 30 days; 205 lifetime likes. Checked Nov 7, 2026. Measures adoption, not quality.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source

Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source

Scores as of Nov 8, 2026. Statistics checked Nov 7, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

At a glance

Parameters: 3.37B
Architecture: deepseek_vl_v2
Context length: 32,768
License: cc-by-nc-4.0
Disk space: 6.3 GB
Software: Transformers

View the model source

MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Best for

Document parsing
Optical character recognition (OCR)
Multilingual document intelligence
Vision-language document understanding
End-to-end document text extraction

Tradeoffs

License is cc-by-nc-4.0, which restricts commercial use
The model card states inference: false
Requires trust_remote_code=True to load custom code
vLLM requires a one-time architecture registration from deepseek_ocr_mtp.py
No separate training or serving package is provided

Ways to run it

Transformers · See official guide

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

import torch
from PIL import Image
from transformers import AutoModelForCausalLM, AutoProcessor

MODEL_ID = 'jinaai/jina-ocr-v1'
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID, dtype=torch.bfloat16, trust_remote_code=True,
).to(device)

image = Image.open('document.png').convert('RGB')
inputs = processor.prepare_ocr_inputs(image, device=device)
output = model.generate(**inputs, max_new_tokens=4096, do_sample=False)
print(processor.decode_ocr(output, inputs['input_ids']))

Official instructions

Explore its uses

SAFETENSORSMULTILINGUALIMAGE-TEXT-TO-TEXT

Keep exploring

Text

Prism ML

Bonsai 2 · 27B

A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.

Freshness 82 out of 100. Release age: 52 days old, Sep 17, 2026. Measures age, not quality.

MODEL SIZE27.36B

LOCALRENTED GPU

Released Sep 17, 2026

Text

DeepSeek

DeepSeek V4.1 Flash

An open-weight model for reasoning, coding, agents, and image understanding. DeepSeek V4.1 Flash combines a 552B backbone with sparse activation and up to one million tokens of context. Choose the original checkpoint or a community uncensored variant below.

Freshness 80 out of 100. Repository age: 59 days old, Sep 10, 2026. Measures age, not quality.

MODEL SIZE552B backbone · 8B active prefill / 16B active decode

LOCALRENTED GPU

Repository opened Sep 10, 2026

Text

Qwen

Qwen3.8

Explore 4 versions of Qwen3.8. Compare model sizes, packages, hardware requirements, and available setups.

4 versionsCompare sizes & formats

LOCALRENTED GPU

Compare versions →