OvisOCR2 needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 17 quants, from 0.0 GB to 1.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
OvisOCR2 – a 0.8B Qwen3.5‑based document parser
OvisOCR2 is a compact 0.8B end‑to‑end model for page‑level document parsing. It converts a document page image into Markdown, including text, formulas, tables, and visual regions. The model is released under the Apache‑2.0 license.
Good at
- Page‑level OCR and Markdown generation
- Handles formulas and tables in natural reading order
- Runs on low‑memory hardware
Limits
- No vision support without the mmproj file
- Limited to 262144 context tokens
- Output token limit of 16384 may be reached on large pages
Best for
- Automated document digitization
- Generating LaTeX‑ready tables
- Batch processing of scanned pages
Who it’s for. Developers and researchers needing a lightweight OCR model that outputs structured Markdown. The model is suitable for integration into document processing pipelines where memory constraints are a concern.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| IQ2_XXS | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ2_XS | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ2_S | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ2_M | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ3_XXS | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q2_K | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q3_K_S | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ3_XS | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ3_S | 0.5 GB | 1.4 GB | Fits | Get file → | |
| IQ3_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q6_K | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 1.7 GB | Fits | Get file → | |
| BF16 | 1.5 GB | 2.4 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.53 GB file, ~1.4 GB memory at 8 k context). For 4 GB VRAM, IQ2_XS or IQ2_S (0.36–0.37 GB file, ~1.3 GB memory). For 2 GB VRAM, IQ2_XXS (0.35 GB file, ~1.3 GB memory).
What GPU do you need for OvisOCR2?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is BF16 (1.5 GB file, about 2.4 GB in use).
Which OvisOCR2 quant should you choose?
Q4_K_M is the usual starting point for OvisOCR2: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.8 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about OvisOCR2
How much VRAM does OvisOCR2 need?
About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run OvisOCR2 on an 8 GB GPU?
Yes, with BF16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of OvisOCR2 GGUF?
It depends on the quant: file is 0.0 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.4 GB, IQ2_M is 0.4 GB, IQ3_XXS is 0.4 GB and 11 more.
What context length does OvisOCR2 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download OvisOCR2 GGUF?
The files are on Hugging Face in the MDfox/OvisOCR2-GGUF-SOTA-20260823 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does OvisOCR2 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run OvisOCR2 on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 1.4 GB of VRAM at 8 k context, which fits within 8 GB.
Does OvisOCR2 support multiple languages?
The model itself does not specify languages; it focuses on document structure and OCR, not language detection.
What is the maximum output token limit?
The model is limited to 16384 output tokens, which may be reached on very large pages.