olmOCR-2-7B-1025 needs about 6.0 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 15.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
Qwen2.5-VL based vision-language model with 7.62B parameters
olmOCR-2-7B-1025 is a vision-language model derived from Qwen2.5-VL-7B-Instruct. It supports image-to-text tasks and can generate structured outputs such as tables and forms. The model is released under the apache-2.0 license.
Good at
- Image text extraction
- Structured data generation
- Visual localization
Limits
- No vision support beyond image input
- Large VRAM requirement for higher quantizations
- No explicit language support listed
Best for
- OCR of scanned documents
- Extracting tables from images
- Generating JSON annotations for images
Who it’s for. Developers needing a lightweight vision-language model for document processing. The model is suitable for applications that require structured output from images and can run on systems with moderate GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ2_XXS | 2.7 GB | 3.6 GB | Fits | Get file → | |
| IQ2_XS | 2.8 GB | 3.8 GB | Fits | Get file → | |
| IQ2_S | 2.9 GB | 3.9 GB | Fits | Get file → | |
| Q2_K_S | 3.0 GB | 4.0 GB | Fits | Get file → | |
| IQ2_M | 3.0 GB | 4.0 GB | Fits | Get file → | |
| Q2_K_M | 3.1 GB | 4.1 GB | Fits | Get file → | |
| IQ3_XXS | 3.5 GB | 4.5 GB | Fits | Get file → | |
| IQ3_XS | 3.6 GB | 4.6 GB | Fits | Get file → | |
| Q3_K_S | 3.9 GB | 4.8 GB | Fits | Get file → | |
| IQ3_M | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q3_K_M | 4.0 GB | 5.0 GB | Fits | Get file → | |
| IQ4_NL | 4.3 GB | 5.3 GB | Fits | Get file → | |
| IQ4_XS | 4.4 GB | 5.3 GB | Fits | Get file → | |
| Q4_K_S | 4.6 GB | 5.6 GB | Fits | Get file → | |
| Q4_1 | 4.8 GB | 5.8 GB | Fits | Get file → | |
| Q4_0 | 4.8 GB | 5.8 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 6.0 GB | Fits | Get file → | |
| Q5_0 | 5.7 GB | 6.6 GB | Fits | Get file → | |
| Q5_K_M | 5.8 GB | 6.8 GB | Fits | Get file → | |
| Q5_1 | 6.1 GB | 7.0 GB | Fits | Get file → | |
| Q6_K_M | 6.5 GB | 7.5 GB | Tight | Get file → | |
| Q8_0 | 8.1 GB | 9.1 GB | Too big | Get file → | |
| F16 | 11.3 GB | 12.3 GB | Too big | Get file → | |
| BF16 | 15.2 GB | 16.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (file size 2.65 GB, estimated memory 3.6 GB). For 12 GB VRAM, Q4_K_M (5.04 GB, 6 GB) or Q5_K_M (5.79 GB, 6.8 GB) are suitable. For 16 GB VRAM, Q8_0 (8.1 GB, 9.1 GB) or BF16 (11.29 GB, 12.3 GB) can be used.
What GPU do you need for olmOCR-2-7B-1025?
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 IQ2_M (3.0 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (5.0 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K_M (6.5 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
- 16 GB VRAM: the best quant that fits is F16 (11.3 GB file, about 12.3 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (15.2 GB file, about 16.2 GB in use).
Which olmOCR-2-7B-1025 quant should you choose?
Q4_K_M is the usual starting point for olmOCR-2-7B-1025: it balances file size and quality well. Here it is a 5.0 GB file.
The Q8_0 file is 8.1 GB, about 1.6 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 olmOCR-2-7B-1025
How much VRAM does olmOCR-2-7B-1025 need?
About 6.0 GB at Q4_K_M with an 8K context window. That is the 5.0 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 olmOCR-2-7B-1025 on an 8 GB GPU?
Yes, with Q6_K_M: the 6.5 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of olmOCR-2-7B-1025 GGUF?
It depends on the quant: file is 0.0 GB, IQ2_XXS is 2.7 GB, IQ2_XS is 2.8 GB, IQ2_S is 2.9 GB, Q2_K_S is 3.0 GB, IQ2_M is 3.0 GB and 19 more.
What context length does olmOCR-2-7B-1025 support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download olmOCR-2-7B-1025 GGUF?
The files are on Hugging Face in the Mungert/olmOCR-2-7B-1025-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 olmOCR-2-7B-1025 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 olmOCR-2-7B-1025 on 8 GB VRAM?
Yes, the IQ2_XXS quantization uses about 3.6 GB of VRAM at 8k context, which fits within 8 GB.
Does the model support multiple languages?
No language information is provided; the model is listed under the apache-2.0 license with no specific language support.
Is the model capable of video understanding?
The parent model supports long video comprehension, but the provided quantizations are for image-to-text tasks only.