What are the hardware requirements for NuExtract 1.5?

NuExtract 1.5 requires approximately 7.7 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed NuExtract 1.5 and how large is it?

NuExtract 1.5 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 1.5?

NuExtract 1.5 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

NuExtract 1.5 by numind — VRAM 7.7GB, 128K context

Name: NuExtract 1.5
Author: numind

NuExtract 1.5 is an open-source language model by numind. Features: 3.8b LLM, VRAM: 7.7GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.18.

Base model:finetune:microsoft/... Base model:microsoft/phi-3.5-m... Conversational Custom code Endpoints compatible Instruct Multilingual Phi3 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/numind/NuExtract-1.5

NuExtract 1.5 Parameters and Internals

Model Type

text-generation, structured information extraction

Use Cases

Areas:

NLP, text extraction

Primary Use Cases:

structured information extraction

Additional Notes

This model is trained to prioritize pure extraction, with a high level of text preservation.

Supported Languages

English (supported), French (supported), Spanish (supported), German (supported), Portuguese (supported), Italian (supported)

Input Output

Input Format:

JSON template

Accepted Modalities:

text

Output Format:

JSON

LLM Name	NuExtract 1.5
Repository 🤗	https://huggingface.co/numind/NuExtract-1.5
Base Model(s)	microsoft/Phi-3.5-mini-instruct microsoft/Phi-3.5-mini-instruct
Model Size	3.8b
Required VRAM	7.7 GB
Updated	2026-07-26
Maintainer	numind
Model Type	phi3
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 2.7 GB: 2-of-2
Model Architecture	Phi3ForCausalLM
License	mit
Context Length	131072
Model Max Length	131072
Transformers Version	4.44.0
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	32064
Torch Data Type	bfloat16

Rank the NuExtract 1.5 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

Quantized Models of the NuExtract 1.5

Model	Likes	Downloads	VRAM
Numind NuExtract 1.5 MLX 8bit	2	21	4 GB

Best Alternatives to NuExtract 1.5

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-1.5.