NuExtract v1.5 needs about 6.1 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 1.3 GB (IQ2_M) to 7.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
NuExtract v1.5 – Phi‑3 based model for structured extraction
NuExtract v1.5 is a fine‑tuned Phi‑3 model focused on extracting structured data from long documents. It supports English, French, Spanish, German, Portuguese, and Italian. The model is released under the MIT license.
Good at
- Long‑document extraction
- Multilingual structured data
- Zero‑shot extraction tasks
Limits
- No vision support
- Requires large VRAM for high‑quality quants
- No temperature tuning beyond 0.0
Best for
- Extracting tables from PDFs
- Parsing legal contracts
- Generating JSON from news articles
Who it’s for. Developers building extraction pipelines that need high‑quality, language‑agnostic output. Researchers testing pure extraction models. Teams that prefer a lightweight, open‑source solution.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 1.3 GB | 5.0 GB | Fits | Get file → | |
| Q2_K | 1.4 GB | 5.1 GB | Fits | Get file → | |
| Q2_K_L | 1.5 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XS | 1.6 GB | 5.3 GB | Fits | Get file → | |
| Q3_K_S | 1.7 GB | 5.4 GB | Fits | Get file → | |
| IQ3_M | 1.9 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_M | 2.0 GB | 5.7 GB | Fits | Get file → | |
| IQ4_XS | 2.1 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_L | 2.1 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_XL | 2.2 GB | 5.9 GB | Fits | Get file → | |
| Q4_0 | 2.2 GB | 5.9 GB | Fits | Get file → | |
| Q4_0 | 2.2 GB | 5.9 GB | Fits | Get file → | |
| Q4_0 | 2.2 GB | 5.9 GB | Fits | Get file → | |
| Q4_0 | 2.2 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_S | 2.2 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_M | 2.4 GB | 6.1 GB | Fits | Get file → | |
| Q4_K_L | 2.5 GB | 6.2 GB | Fits | Get file → | |
| Q5_K_S | 2.6 GB | 6.4 GB | Fits | Get file → | |
| Q5_K_M | 2.8 GB | 6.5 GB | Fits | Get file → | |
| Q5_K_L | 2.9 GB | 6.6 GB | Fits | Get file → | |
| Q6_K | 3.1 GB | 6.9 GB | Fits | Get file → | |
| Q6_K_L | 3.2 GB | 6.9 GB | Fits | Get file → | |
| Q8_0 | 4.1 GB | 7.8 GB | Tight | Get file → | |
| F16 | 7.6 GB | 11.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 2.39 GB, memory 6.1 GB). For 12 GB VRAM, Q5_K_M (file size 2.82 GB, memory 6.5 GB) offers better quality. If you have 16 GB or more, Q6_K (file size 3.14 GB, memory 6.9 GB) provides the highest fidelity.
What GPU do you need for NuExtract v1.5?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q4_K_S (2.2 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (7.6 GB file, about 11.4 GB in use).
Which NuExtract v1.5 quant should you choose?
Q4_K_M is the usual starting point for NuExtract v1.5: it balances file size and quality well. Here it is a 2.4 GB file.
The Q8_0 file is 4.1 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 IQ2_M at 1.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about NuExtract v1.5
How much VRAM does NuExtract v1.5 need?
About 6.1 GB at Q4_K_M with an 8K context window. That is the 2.4 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 v1.5 on an 8 GB GPU?
Yes, with Q8_0: the 4.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NuExtract v1.5 GGUF?
It depends on the quant: IQ2_M is 1.3 GB, Q2_K is 1.4 GB, Q2_K_L is 1.5 GB, IQ3_XS is 1.6 GB, Q3_K_S is 1.7 GB, IQ3_M is 1.9 GB and 18 more.
What context length does NuExtract v1.5 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.
Where can I download NuExtract v1.5 GGUF?
The files are on Hugging Face in the bartowski/NuExtract-v1.5-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 v1.5 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 v1.5 on 8 GB VRAM?
Yes, a Q4_K_M quant will fit on 8 GB VRAM with an estimated memory usage of 6.1 GB at 8k context.
Does NuExtract support vision inputs?
No, the model does not support vision or image inputs.
What temperature should I use for extraction?
Use a temperature close to 0.0 for best extraction fidelity; higher temperatures degrade precision.