What are the hardware requirements for NuExtract?

NuExtract requires approximately 15.4 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed NuExtract and how large is it?

NuExtract is developed by numind, a model with 3.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate NuExtract?

NuExtract is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

NuExtract by numind — VRAM 15.4GB, 4K context

Name: NuExtract
Author: numind

NuExtract is an open-source language model by numind. Features: 3.8b LLM, VRAM: 15.4GB, Context: 4K, License: mit, Instruction-Based, LLM Explorer Score: 0.14.

Base model:finetune:microsoft/... Base model:microsoft/phi-3-min... Conversational Custom code En Endpoints compatible Instruct Phi3 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/numind/NuExtract

NuExtract Parameters and Internals

Model Type

Information Extraction

Use Cases

Areas:

Information Extraction

Additional Notes

This model is out-dated. Find the updated version at the provided link.

Supported Languages

en (Unknown proficiency)

Training Details

Methodology:

Fine-tuned on a private high-quality synthetic dataset for information extraction.

Context Length:

2000

Input Output

Input Format:

Input text (less than 2000 tokens) and a JSON template describing the information to extract.

Accepted Modalities:

text

Output Format:

JSON formatted output based on provided template.

Performance Tips:

Provide an example of output formatting to help the model understand your task more precisely.

LLM Name	NuExtract
Repository 🤗	https://huggingface.co/numind/NuExtract
Base Model(s)	Phi 3 Mini 4K Instruct microsoft/Phi-3-mini-4k-instruct
Model Size	3.8b
Required VRAM	15.4 GB
Updated	2026-08-06
Maintainer	numind
Model Type	phi3
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 0.4 GB: 4-of-4
Supported Languages	en
Model Architecture	Phi3ForCausalLM
License	mit
Context Length	4096
Model Max Length	4096
Transformers Version	4.42.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<\|end-output\|>
Vocabulary Size	32064
Torch Data Type	float32

Rank the NuExtract capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to NuExtract

Best Alternatives	Context / RAM	Downloads	Likes
Phi 4 Mini Instruct	128K / 7.7 GB	514603	791
Phi 3.5 Mini Instruct	128K / 7.7 GB	1164079	999
Phi 3 Mini 128K Instruct	128K / 7.7 GB	233663	1700
Phi 3 Mini 128K Instruct	128K / 7.7 GB	7	0
Phi 4 Mini Abliterated	128K / 7.7 GB	33	1
Phi 3 Mini 128K Instruct	128K / 7.7 GB	11	0
Phi 4 Mini Instruct Heretic	128K / 7.7 GB	13	0
Phi 3.5 Mini TitanFusion 0.1	128K / 7.7 GB	7	0
NuExtract V1.5	128K / 7.7 GB	108511	89
MediPhi Instruct	128K / 7.7 GB	1671	69

Note: green Score (e.g. "73.2") means that the model is better than numind/NuExtract.