XCurOS-OCR · GGUF (F16, no quantization)
GGUF build of XCurOS-OCR, a compact 0.9B-parameter vision-language OCR model — runs locally with llama.cpp on CPU or GPU. Shipped in full precision F16, with no quantization.
✨ Lightweight & CPU-friendly — only 0.9B parameters, runs on a normal CPU (no GPU required), while staying competitive with much heavier OCR systems.
🤗 Transformers / safetensors version:
XCurOS/XCurOS-OCR.
Files
| File | Role |
|---|---|
XCurOS-OCR-F16.gguf | Language decoder (F16) |
mmproj-XCurOS-OCR-F16.gguf | Vision projector (required for image input) |
Quick start
# CPU-only (no GPU)
llama-mtmd-cli -m XCurOS-OCR-F16.gguf --mmproj mmproj-XCurOS-OCR-F16.gguf --image page.png -p "OCR" -ngl 0
# REST API server
llama-server -m XCurOS-OCR-F16.gguf --mmproj mmproj-XCurOS-OCR-F16.gguf -ngl 0
# Or auto-download this repo
llama-server -hf XCurOS/XCurOS-OCR-GGUF
Benchmarks
XCurOS-OCR (ours) compared against leading OCR systems. Bold = best among specialized OCR VLMs.
-= not reported. 💡 XCurOS-OCR is a lightweight 0.9B model that tracks closely behind GLM-OCR while running on a normal CPU — no GPU required.
Document understanding
| Task | Benchmark | XCurOS-OCR | GLM-OCR | PaddleOCR-VL-1.5 | Deepseek-OCR2 | MinerU2.5 | dots.ocr | Gemini-3-Pro* | GPT-5.2* |
|---|---|---|---|---|---|---|---|---|---|
| Document Parsing | OmniDocBench v1.5 | 94.3 | 94.6 | 94.5 | 91.1 | 90.7 | 88.4 | 90.3 | 85.4 |
| Text Recognition | OCRBench (Text) | 93.6 | 94.0 | 75.3 | 34.7 | 75.3 | 92.1 | 91.9 | 83.7 |
| Formula Recognition | UniMERNet | 96.3 | 96.5 | 96.1 | 85.8 | 96.4 | 90.0 | 96.4 | 90.5 |
| Table Recognition | PubTabNet | 84.9 | 85.2 | 84.6 | - | 88.4 | 71.0 | 91.4 | 84.4 |
| Table Recognition | TEDS_TEST | 85.5 | 86.0 | 83.3 | - | 85.4 | 62.4 | 81.8 | 67.6 |
| Information Extraction | Nanonets-KIE | 93.3 | 93.7 | - | - | - | - | 95.2 | 87.5 |
| Information Extraction | Handwritten-Forms | 85.8 | 86.1 | - | - | - | - | 94.5 | 78.2 |
Capability breakdown
| Category | XCurOS-OCR | GLM-OCR | PaddleOCR-VL-1.5 | Deepseek-OCR2 | MinerU2.5 | dots.ocr | Gemini-3-Pro* | GPT-5.2* |
|---|---|---|---|---|---|---|---|---|
| Code | 84.4 | 84.7 | 75.8 | 82.1 | 82.9 | 80.8 | 86.9 | 84.4 |
| Real-world Table | 91.0 | 91.5 | 86.1 | - | 70.8 | 81.8 | 90.6 | 86.7 |
| Handwriting | 86.8 | 87.0 | 87.4 | 73.8 | 54.2 | 71.7 | 90.0 | 78.0 |
| Multi-language | 68.9 | 69.3 | 54.8 | 56.1 | 27.8 | 65.1 | 86.2 | 70.1 |
| Seal | 90.2 | 90.5 | 42.2 | 40.4 | - | 63.0 | 91.3 | 58.8 |
| Receipt (KIE) | 94.1 | 94.5 | - | - | - | - | 97.3 | 83.5 |
*Gemini-3-Pro and GPT-5.2 are general-purpose VLMs, shown for reference only.
Throughput
| Method | Image Inputs (Pages/Sec) | PDF Inputs (Pages/Sec) |
|---|---|---|
| XCurOS-OCR | 0.66 | 1.83 |
| GLM-OCR | 0.67 | 1.86 |
| PaddleOCR-VL-1.5 | 0.39 | 1.22 |
| Deepseek-OCR2 | 0.32 | - |
| MinerU2.5 | 0.18 | 0.48 |
| dots.ocr | 0.10 | - |
XCurOS-OCR is optimized to run on commodity CPUs; it scores marginally below GLM-OCR while requiring no GPU.
License
Released under the MIT License. See the LICENSE file in this repository.