NuExtract 2.0 2B needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.5 GB (TQ1_0) to 3.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.
NuExtract 2.0 2B – multimodal extraction model
NuExtract 2.0 2B is a 1.54B parameter model based on Qwen2VL. It extracts structured data from text and image inputs using a JSON template. The model supports multilingual inputs and is licensed under MIT.
Good at
- Structured extraction from text and images
- JSON template driven extraction
- Multilingual support
Limits
- No vision support beyond image inputs
- Limited to 32768 token context
- No commercial license restrictions
Best for
- Extracting form data from scanned documents
- Parsing invoices and receipts
- Automating data entry tasks
Who it’s for. Developers building extraction pipelines that require both text and image understanding. The model is suitable for applications needing structured output in JSON format.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 0.5 GB | 1.2 GB | Fits | Get file → | |
| TQ2_0 | 0.5 GB | 1.3 GB | Fits | Get file → | |
| Q2_K | 0.7 GB | 1.4 GB | Fits | Get file → | |
| IQ3_XS | 0.7 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_S | 0.8 GB | 1.5 GB | Fits | Get file → | |
| IQ3_S | 0.8 GB | 1.5 GB | Fits | Get file → | |
| IQ3_M | 0.8 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_M | 0.8 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_L | 0.9 GB | 1.6 GB | Fits | Get file → | |
| IQ4_XS | 0.9 GB | 1.6 GB | Fits | Get file → | |
| Q4_0 | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_S | 0.9 GB | 1.7 GB | Fits | Get file → | |
| IQ4_NL | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_M | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q4_1 | 1.0 GB | 1.8 GB | Fits | Get file → | |
| Q5_0 | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_S | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_M | 1.1 GB | 1.9 GB | Fits | Get file → | |
| Q5_1 | 1.2 GB | 1.9 GB | Fits | Get file → | |
| Q6_K | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q8_0 | 1.6 GB | 2.4 GB | Fits | Get file → | |
| BF16 | 3.1 GB | 3.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 (0.93 GB, 1.7 GB memory) or Q5_0 (1.1 GB, 1.8 GB memory). For 12 GB VRAM, Q5_K_M (1.13 GB, 1.9 GB memory) or Q6_K (1.27 GB, 2 GB memory) are suitable. Larger VRAM allows Q8_0 (1.65 GB, 2.4 GB memory).
What GPU do you need for NuExtract 2.0 2B?
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 (3.1 GB file, about 3.8 GB in use).
Which NuExtract 2.0 2B quant should you choose?
Q4_K_M is the usual starting point for NuExtract 2.0 2B: it balances file size and quality well. Here it is a 1.0 GB file.
The Q8_0 file is 1.6 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 TQ1_0 at 0.5 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about NuExtract 2.0 2B
How much VRAM does NuExtract 2.0 2B need?
About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.0 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 NuExtract 2.0 2B on an 8 GB GPU?
Yes, with BF16: the 3.1 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NuExtract 2.0 2B GGUF?
It depends on the quant: TQ1_0 is 0.5 GB, TQ2_0 is 0.5 GB, Q2_K is 0.7 GB, IQ3_XS is 0.7 GB, Q3_K_S is 0.8 GB, IQ3_S is 0.8 GB and 16 more.
What context length does NuExtract 2.0 2B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.
Where can I download NuExtract 2.0 2B GGUF?
The files are on Hugging Face in the numind/NuExtract-2.0-2B-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 NuExtract 2.0 2B use?
Hugging Face lists the license as mit. 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 NuExtract 2.0 2B on 8 GB VRAM?
Yes, using the Q4_0 quantization (0.93 GB file, 1.7 GB memory) fits within 8 GB VRAM.
Does the model support vision tasks?
Yes, it can process image inputs as part of multimodal extraction.
What license applies to this model?
The model is released under the MIT license.