datalab-to / image-text-to-text updated 1 month ago

chandra-ocr-2

Name: chandra-ocr-2
Author: datalab-to

Chandra 2 is a state of the art OCR model from Datalab that outputs markdown, HTML, and JSON. It is highly accurate at extracting text from images and PDFs, while preserving layout information.

Params

5.3 B

Context

—

Downloads 30d

3.2 M

Likes

466

Commercial use: conditional · openrail Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

3.2 M2.9 M

Jul 28Jul 31Aug 3Aug 6

Can you run it?

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

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	10.6 GB	12.9 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: Qwen3_5ForConditionalGeneration
Parameters: 5.3 B
Tensor type: BF16
Licence: openrail
First seen on the Hub: 2026-03-16
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3.5-9B 12.4 M Qwen2.5-VL-7B-Instruct 9.3 M Qwen2.5-VL-3B-Instruct 8.2 M Qwen3.5-4B 6.7 M Qwen3-VL-8B-Instruct 4.9 M Qwen3-VL-4B-Instruct 4.0 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB