WE

WeVisDoc 4B

WevisdocGGUF by prithivMLmodsUpdated 2026-09-18
Download on Hugging Face
Parameters4.41B
Context256K
Layers36
Architectureqwen3vl
Smallest quant2.2 GB
Quick answer

WeVisDoc 4B needs about 4.4 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 2.2 GB (Q3_K_M) to 8.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

WeVisDoc 4B – end‑to‑end document parsing with vision and text

WeVisDoc 4B is a vision‑language model fine‑tuned for converting page images into structured Markdown, LaTeX formulas, and HTML tables. It is based on Qwen3VL and achieves top scores on OmniDocBench and PureDocBench. The model is released under Apache‑2.0.

Good at

  • Vision‑enabled document parsing
  • Structured Markdown output
  • LaTeX and HTML table generation

Limits

  • No general‑purpose vision tasks
  • Requires 8k context for full performance
  • No GPU‑specific optimizations listed

Best for

  • Automated PDF conversion
  • Academic paper digitization
  • Legal document extraction

Who it’s for. Developers building document processing pipelines and researchers needing high‑quality OCR with structured output. The model is suitable for applications that require both image understanding and text generation in a single pass.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M2.2 GB 4.0 GB
Fits Get file →
Q3_K_L2.4 GB 4.1 GB
Fits Get file →
Q4_K_S2.6 GB 4.3 GB
Fits Get file →
Q4_K_M2.7 GB 4.4 GB
Fits Get file →
Q5_K_S3.1 GB 4.8 GB
Fits Get file →
Q5_K_M3.2 GB 4.9 GB
Fits Get file →
Q6_K3.6 GB 5.3 GB
Fits Get file →
Q8_04.7 GB 6.4 GB
Fits Get file →
BF168.8 GB 10.5 GB
Too big Get file →
F168.8 GB 10.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.72 GB, estimated 4.4 GB memory). For 12 GB VRAM, Q5_K_M (3.16 GB, 4.9 GB memory) or Q6_K (3.63 GB, 5.3 GB memory) are suitable. For larger budgets, Q8_0 (4.69 GB, 6.4 GB memory) or BF16/F16 (8.83 GB, 10.5 GB memory) provide higher precision.

What GPU do you need for WeVisDoc 4B?

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 Q3_K_M (2.2 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.7 GB file, about 6.4 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.8 GB file, about 10.5 GB in use).

Which WeVisDoc 4B quant should you choose?

Q4_K_M is the usual starting point for WeVisDoc 4B: it balances file size and quality well. Here it is a 2.7 GB file.

The Q8_0 file is 4.7 GB, about 1.7 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 2.2 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

Architectureqwen3vl
Parameters4.41B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized byprithivMLmods
FamilyWevisdoc
Licenseapache-2.0
Downloads (HF)753
Last updated2026-09-18

Frequently asked questions about WeVisDoc 4B

How much VRAM does WeVisDoc 4B need?

About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.7 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 WeVisDoc 4B on an 8 GB GPU?

Yes, with Q8_0: the 4.7 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of WeVisDoc 4B GGUF?

It depends on the quant: Q3_K_M is 2.2 GB, Q3_K_L is 2.4 GB, Q4_K_S is 2.6 GB, Q4_K_M is 2.7 GB, Q5_K_S is 3.1 GB, Q5_K_M is 3.2 GB and 4 more.

What context length does WeVisDoc 4B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download WeVisDoc 4B GGUF?

The files are on Hugging Face in the prithivMLmods/WeVisDoc-4B-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 WeVisDoc 4B 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 WeVisDoc 4B on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 4.4 GB memory at 8k context, which fits within 8 GB VRAM.

Does WeVisDoc 4B support Chinese text?

Yes, the model supports both English and Chinese, as indicated by the dual‑language description.

What license applies to WeVisDoc 4B?

The model is released under the Apache‑2.0 license.

Other GGUFs of WeVisDoc-4B

Similar models

Browse all →

More from prithivMLmods

All by prithivMLmods →

More Wevisdoc models

All Wevisdoc →

Other small models

All small models →