NU

NuExtract 1.5 Smol

NuextractGGUF by bartowskiUpdated 2024-11-21
Download on Hugging Face
Parameters1.71B
Context8K
Layers24
Architecturellama
Smallest quant0.7 GB
Quick answer

NuExtract 1.5 Smol needs about 3.2 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 21 quants, from 0.7 GB (Q2_K) to 3.4 GB (F16).

NuExtract 1.5 Smol – compact structured extraction model

NuExtract 1.5 Smol is a 1.71B‑parameter llama model fine‑tuned for structured information extraction. It supports multiple languages and is designed for pure extraction tasks with minimal temperature. The model is released under the MIT license.

Good at

  • Structured data extraction
  • Low‑temperature inference
  • Multilingual support

Limits

  • No vision capabilities
  • Requires 8k context for full performance
  • No explicit benchmark scores

Best for

  • Extracting tables from text
  • Generating JSON from documents
  • Automating form filling

Who it’s for. Developers building extraction pipelines who need a lightweight, open‑source model. The model is suitable for edge deployments and local inference with llama.cpp or LM Studio.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.7 GB 2.8 GB
Fits Get file →
Q2_K_L0.7 GB 2.8 GB
Fits Get file →
Q3_K_S0.8 GB 2.9 GB
Fits Get file →
IQ3_M0.8 GB 2.9 GB
Fits Get file →
Q3_K_L0.9 GB 3.0 GB
Fits Get file →
IQ4_XS0.9 GB 3.1 GB
Fits Get file →
Q3_K_XL1.0 GB 3.1 GB
Fits Get file →
Q4_01.0 GB 3.1 GB
Fits Get file →
Q4_01.0 GB 3.1 GB
Fits Get file →
Q4_01.0 GB 3.1 GB
Fits Get file →
Q4_01.0 GB 3.1 GB
Fits Get file →
Q4_K_S1.0 GB 3.1 GB
Fits Get file →
Q4_K_M1.1 GB 3.2 GB
Fits Get file →
Q4_K_L1.1 GB 3.2 GB
Fits Get file →
Q5_K_S1.2 GB 3.3 GB
Fits Get file →
Q5_K_M1.2 GB 3.3 GB
Fits Get file →
Q5_K_L1.2 GB 3.4 GB
Fits Get file →
Q6_K1.4 GB 3.5 GB
Fits Get file →
Q6_K_L1.4 GB 3.5 GB
Fits Get file →
Q8_01.8 GB 3.9 GB
Fits Get file →
F163.4 GB 5.5 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (1.06 GB, 3.2 GB memory) or Q5_K_M (1.23 GB, 3.3 GB memory) are good choices. For 4 GB VRAM, Q3_K_S (0.78 GB, 2.9 GB memory) or Q2_K (0.67 GB, 2.8 GB memory) fit comfortably. Memory estimates are approximate.

What GPU do you need for NuExtract 1.5 Smol?

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 (1.8 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.4 GB file, about 5.5 GB in use).

Which NuExtract 1.5 Smol quant should you choose?

Q4_K_M is the usual starting point for NuExtract 1.5 Smol: it balances file size and quality well. Here it is a 1.1 GB file.

The Q8_0 file is 1.8 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 Q2_K at 0.7 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

Architecturellama
Parameters1.71B
Layers24
Trained context8,192 tokens
KV cache (fp16)192 KB per token

Source

Quantized bybartowski
FamilyNuextract
Licensemit
Downloads (HF)570
Last updated2024-11-21

Frequently asked questions about NuExtract 1.5 Smol

How much VRAM does NuExtract 1.5 Smol need?

About 3.2 GB at Q4_K_M with an 8K context window. That is the 1.1 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 NuExtract 1.5 Smol on an 8 GB GPU?

Yes, with F16: the 3.4 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NuExtract 1.5 Smol GGUF?

It depends on the quant: Q2_K is 0.7 GB, Q2_K_L is 0.7 GB, Q3_K_S is 0.8 GB, IQ3_M is 0.8 GB, Q3_K_L is 0.9 GB, IQ4_XS is 0.9 GB and 15 more.

What context length does NuExtract 1.5 Smol support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.

Where can I download NuExtract 1.5 Smol GGUF?

The files are on Hugging Face in the bartowski/NuExtract-1.5-smol-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 Smol 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 Smol on 8 GB VRAM?

Yes, use Q4_K_M or Q5_K_M quantizations; they require about 3.2–3.3 GB of VRAM at 8k context.

Does the model support vision tasks?

No, the model is purely text‑based and has no vision capabilities.

What temperature should I use for extraction?

Use a temperature close to 0 for best extraction fidelity; higher temperatures degrade accuracy.

Other GGUFs of NuExtract-1.5-smol

Similar models

Browse all →

More from bartowski

All by bartowski →

More Nuextract models

All Nuextract →

Other tiny models

All tiny models →