OV

OvisOCR3

OvisocrGGUF by prithivMLmodsUpdated 2026-10-29
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant0.5 GB
Quick answer

OvisOCR3 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 9 quants, from 0.5 GB (Q3_K_M) to 1.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

0.8B multimodal OCR and document‑understanding model

OvisOCR3 is a 0.8B parameter model built on Qwen3.5‑0.8B. It unifies document parsing, general OCR, key information extraction, figure captioning, and cross‑page table reconstruction. The model is trained in four stages and supports Markdown and structured JSON outputs.

Good at

  • OCR and document parsing
  • Key information extraction
  • Cross‑page table reconstruction

Limits

  • No vision support beyond OCR
  • Requires GPU with vLLM
  • License is Apache‑2.0

Best for

  • OCR in document workflows
  • Document parsing in batch processing
  • Table reconstruction across multi‑page PDFs

Who it’s for. Developers needing a single compact model for OCR and document understanding tasks. Researchers working on multimodal document AI who prefer an open‑weight solution.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M0.5 GB 1.4 GB
Fits Get file →
Q3_K_L0.5 GB 1.4 GB
Fits Get file →
Q4_K_S0.5 GB 1.4 GB
Fits Get file →
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q5_K_S0.6 GB 1.5 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q6_K0.6 GB 1.5 GB
Fits Get file →
Q8_00.8 GB 1.7 GB
Fits Get file →
BF161.5 GB 2.4 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.53 GB, 1.4 GB memory). For 12 GB VRAM, Q5_K_M (0.58 GB, 1.5 GB memory) or Q6_K (0.63 GB, 1.5 GB memory). For 16 GB VRAM, Q8_0 (0.81 GB, 1.7 GB memory) or BF16 (1.52 GB, 2.4 GB memory).

What GPU do you need for OvisOCR3?

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 OvisOCR3 quant should you choose?

Q4_K_M is the usual starting point for OvisOCR3: 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 Q3_K_M at 0.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters752M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized byprithivMLmods
FamilyOvisocr
Licenseapache-2.0
Downloads (HF)1,009
Last updated2026-10-29

Frequently asked questions about OvisOCR3

How much VRAM does OvisOCR3 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 OvisOCR3 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 OvisOCR3 GGUF?

It depends on the quant: Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, Q4_K_S is 0.5 GB, Q4_K_M is 0.5 GB, Q5_K_S is 0.6 GB, Q5_K_M is 0.6 GB and 3 more.

What context length does OvisOCR3 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 OvisOCR3 GGUF?

The files are on Hugging Face in the prithivMLmods/ATH-MaaS-OvisOCR3-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does OvisOCR3 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 OvisOCR3 on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires about 1.4 GB memory at 8 k context.

Does OvisOCR3 support image inputs?

It is designed for OCR and document understanding; it does not provide general vision capabilities beyond text spotting.

Other GGUFs of OvisOCR3

Similar models

Browse all →

More from prithivMLmods

All by prithivMLmods →

More Ovisocr models

All Ovisocr →

Other tiny models

All tiny models →