NuExtract 1.5 tiny needs about 1.1 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 0.4 GB (Q3_K_S) to 0.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.
NuExtract 1.5 tiny – a small Qwen2.5 fine‑tuned for structured extraction
NuExtract 1.5 tiny is a 0.63B parameter model based on Qwen2.5‑0.5B. It is fine‑tuned for extracting structured data from text. The model supports long documents up to 32,768 tokens and works in multiple languages.
Good at
- Structured data extraction
- Long‑document support
- Multilingual extraction
Limits
- No vision support
- Limited instruction tuning
- Requires post‑training for chat
Best for
- Extracting tables from PDFs
- Generating JSON from reports
- Parsing multilingual forms
Who it’s for. Developers building extraction pipelines who need a lightweight, open‑source model. The model is suitable for edge deployments and low‑resource environments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q2_K | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_0 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q3_K_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q3_K_L | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_1 | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_S | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q5_0 | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q5_K_S | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q5_1 | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q5_K_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q6_K | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q8_0 | 0.7 GB | 1.3 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_1 (0.46 GB file, ~1.1 GB memory) or Q4_K_M (0.49 GB file, ~1.1 GB memory). If 4 GB VRAM is available, Q3_K_S (0.41 GB file, ~1 GB memory) is a good balance between size and performance. Larger quants like Q6_K (0.65 GB file, ~1.3 GB memory) require more VRAM.
What GPU do you need for NuExtract 1.5 tiny?
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 Q8_0 (0.7 GB file, about 1.3 GB in use).
Which NuExtract 1.5 tiny quant should you choose?
Q4_K_M is the usual starting point for NuExtract 1.5 tiny: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.7 GB, about 1.4 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_S at 0.4 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
Source
Frequently asked questions about NuExtract 1.5 tiny
How much VRAM does NuExtract 1.5 tiny need?
About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.5 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 1.5 tiny on an 8 GB GPU?
Yes, with Q8_0: the 0.7 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NuExtract 1.5 tiny GGUF?
It depends on the quant: Q3_K_S is 0.4 GB, Q2_K is 0.4 GB, Q4_0 is 0.4 GB, Q3_K_M is 0.4 GB, Q3_K_L is 0.4 GB, Q4_1 is 0.5 GB and 8 more.
What context length does NuExtract 1.5 tiny support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.
Where can I download NuExtract 1.5 tiny GGUF?
The files are on Hugging Face in the QuantFactory/NuExtract-1.5-tiny-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 1.5 tiny 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 1.5 tiny on 8 GB VRAM?
Yes. Use Q4_1 or Q4_K_M quant, which require about 1.1 GB VRAM at 8K context.
Does this model support image input?
No, it is a text‑only model.
What license does it use?
The model is released under the MIT license.