surya-ocr-2
- Accuracy - scores 83.3% on olmOCR-bench (top under 3B params) - Speed - throughput of 5 pages/s on an RTX 5090 - Multilingual - scores 87.2% on an internal benchmark set of 91 languages (more here) - Layout analysis (table, image, header, etc.) with reading order - Table recognition (rows + columns)
Params
690 M
Context
—
Downloads 30d
1.2 M
Likes
111
Download history
daily snapshots · 55 days
▲ 45 K in the last 30 days (3.5%)
1.4 M1.2 M
Aug 22Sep 1Sep 11Sep 20
1.5 M873 K
Jul 28Aug 15Sep 2Sep 20
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 | 1.4 GB | 2.1 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
- 690 M
- Tensor type
- BF16
- Licence
- openrail
- First seen on the Hub
- 2026-05-14
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any image-text-to-text model
Popular comparisons
Appears in