Qianfan-OCR needs about 4.8 GB of memory at Q4_K_M (a 3.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 20 quants, from 0.0 GB to 8.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Qianfan-OCR – 4.42B parameter vision‑language model for document intelligence
Qianfan-OCR is a 4.42B parameter end‑to‑end document intelligence model. It performs direct image‑to‑Markdown conversion and supports structured parsing, table extraction, chart understanding, and question answering. The model is trained on 32768 context tokens and released under apache‑2.0.
Good at
- End‑to‑end OCR and layout analysis
- Multilingual document parsing
- Prompt‑driven information extraction
Limits
- No mixture of experts
- Requires large VRAM for higher quant levels
- No explicit vision‑only mode
Best for
- Document digitization pipelines
- Table and chart extraction tasks
- Multilingual OCR applications
Who it’s for. Developers building OCR or document understanding solutions who need a single model for parsing, layout, and comprehension. The model is suitable for applications requiring multilingual support and prompt‑driven extraction.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| IQ3_XXS | 2.1 GB | 3.8 GB | Fits | Get file → | |
| IQ3_XS | 2.1 GB | 3.8 GB | Fits | Get file → | |
| IQ3_M | 2.3 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_S | 2.3 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_M | 2.5 GB | 4.2 GB | Fits | Get file → | |
| IQ4_NL | 2.5 GB | 4.2 GB | Fits | Get file → | |
| IQ4_XS | 2.6 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_S | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q4_1 | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q4_0 | 2.9 GB | 4.6 GB | Fits | Get file → | |
| Q4_K_M | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q5_0 | 3.3 GB | 5.0 GB | Fits | Get file → | |
| Q5_K_M | 3.5 GB | 5.2 GB | Fits | Get file → | |
| Q5_1 | 3.6 GB | 5.3 GB | Fits | Get file → | |
| Q6_K_M | 3.8 GB | 5.5 GB | Fits | Get file → | |
| Q8_0 | 4.7 GB | 6.4 GB | Fits | Get file → | |
| BF16 | 6.7 GB | 8.4 GB | Too big | Get file → | |
| F16 | 6.7 GB | 8.4 GB | Too big | Get file → | |
| BF16 | 8.8 GB | 10.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (file size 2.33 GB, memory 4 GB at 8 k context). For 12 GB VRAM, Q5_K_M (file size 3.48 GB, memory 5.2 GB). For 16 GB VRAM, Q6_K_M (file size 3.82 GB, memory 5.5 GB).
What GPU do you need for Qianfan-OCR?
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_S (2.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K_M (3.8 GB file, about 5.5 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 10.6 GB in use).
Which Qianfan-OCR quant should you choose?
Q4_K_M is the usual starting point for Qianfan-OCR: it balances file size and quality well. Here it is a 3.1 GB file.
The Q8_0 file is 4.7 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 Qianfan-OCR
How much VRAM does Qianfan-OCR need?
About 4.8 GB at Q4_K_M with an 8K context window. That is the 3.1 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 Qianfan-OCR 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 Qianfan-OCR GGUF?
It depends on the quant: file is 0.0 GB, IQ3_XXS is 2.1 GB, IQ3_XS is 2.1 GB, IQ3_M is 2.3 GB, Q3_K_S is 2.3 GB, Q3_K_M is 2.5 GB and 14 more.
What context length does Qianfan-OCR support?
The GGUF header lists a trained context length of 32,768 tokens (32K). 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 Qianfan-OCR GGUF?
The files are on Hugging Face in the Mungert/Qianfan-OCR-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 Qianfan-OCR 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 Qianfan‑OCR on 8 GB VRAM?
Yes, using Q4_K_S quantization requires about 4 GB memory at 8 k context, which fits within 8 GB VRAM.
Does Qianfan‑OCR support vision tasks?
Yes, it includes vision capabilities for image‑to‑Markdown conversion and layout analysis.