---
language:
- en
- es
- fr
- de
- it
- pt
license: mit
tags:
- odooclaw
- odoo
- ocr
- vision
- document-parsing
- invoice
- gguf
- llama-cpp
pipeline_tag: image-to-text
base_model: zai-org/GLM-OCR
library_name: gguf
---

# odooclaw-vision

Vision model for **OdooClaw** — on-premise document extraction (invoices, delivery notes) with no cloud dependencies.

**Base model**: [zai-org/GLM-OCR](https://huggingface.co/zai-org/GLM-OCR) (0.9B params, MIT license) — the best quality-per-parameter OCR of 2026, exceptional at tables and structured documents. GGUF conversion by [ggml-org](https://huggingface.co/ggml-org/GLM-OCR-GGUF).

## Files

| File | Size | Description |
|---|---|---|
| `odooclaw-vision-Q5_K_M.gguf` | ~610 MB | Main model (Q5_K_M quantization) |
| `mmproj-odooclaw-vision-Q8_0.gguf` | ~462 MB | Multimodal projector (mmproj) for llama.cpp |

## Usage with llama.cpp

```bash
llama-server \
  -m odooclaw-vision-Q5_K_M.gguf \
  --mmproj mmproj-odooclaw-vision-Q8_0.gguf \
  --host 0.0.0.0 --port 8093 \
  -c 8192 --parallel 1 --temp 0.0 \
  --alias odooclaw-vision
```

OpenAI-compatible endpoint:

```bash
curl http://localhost:8093/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "odooclaw-vision",
    "messages": [{"role": "user", "content": [
      {"type": "image_url", "image_url": {"url": "data:image/png;base64,<BASE64>"}},
      {"type": "text", "text": "Extract all text from this invoice document, preserving table structure."}
    ]}],
    "temperature": 0,
    "max_tokens": 2048
  }'
```

## OdooClaw pipeline architecture

```
Invoice PDF → odooclaw-vision (image → structured text)
            → odooclaw-light (text → JSON: partner, vat, ref, date, total, lines)
            → business rules (validation: reverse charge, currency, sanity checks)
            → account_dynamic_rules (Odoo rules: account, analytics, taxes)
            → vendor bill in Odoo
```

## Performance

- **CPU (N100, 4 cores)**: ~1-5 min per page at 96 dpi
- **Quality**: totals, partners, dates and line items extracted correctly from real production invoices (SIEPER, utilities, telecom)

## License

MIT. Commercial use allowed.