Downloads · 30 days
90
32% of all-time downloads
OvisOCR2-AWQ
Ar4ikov/OvisOCR2-AWQ
OvisOCR2-AWQ is a image-text-to-text model from Ar4ikov. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
AWQ (W4A16 asymmetric, group size 128) quantization of ATH-MaaS/OvisOCR2 — a 0.8B end-to-end document parsing / OCR model built on Qwen3.5-0.8B.
All-time downloads
279
Public
Parameters
1.1B
1.5 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors1.5 GB · 99%
Parameter types
How the weights are stored.
BF16614M · 55%
Try a prompt
Base models
Model card
From the Hugging Face model README
OvisOCR2-AWQ
AWQ (W4A16 asymmetric, group size 128) quantization of ATH-MaaS/OvisOCR2 — a 0.8B end-to-end document parsing / OCR model built on Qwen3.5-0.8B.
Made with llm-compressor: AWQModifier applied to all Linear layers of the language model. The vision tower and lm_head are kept in BF16.
- Calibration: 256 samples from
HuggingFaceH4/ultrachat_200k, max sequence length 2048 - Scheme:
W4A16_ASYM - Ignored modules:
lm_head,visual.*(vision tower)
Usage (vLLM)
vllm serve <this-repo> --trust-remote-code=false
Prompt for full-page OCR (same as base model):
Extract all readable content from the image in natural human reading order and output the result as a single Markdown document. Format formulas as LaTeX. Format tables as HTML: <table>...</table>. Preserve the original text without translation.
Use temperature 0.0 for OCR tasks.
Notes
Quantized entirely with open tooling; see the base model card for benchmarks, capabilities and limitations of the underlying model. Weight-only 4-bit quantization may introduce a small accuracy loss versus BF16 on dense documents.
- Task
- Image-Text-to-Text
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026