What are the hardware requirements for NuExtract 1.5 Smol?

NuExtract 1.5 Smol requires approximately 3.4 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed NuExtract 1.5 Smol and how large is it?

NuExtract 1.5 Smol is developed by numind, a model with 1.7b 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 Smol?

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

NuExtract 1.5 Smol by numind — VRAM 3.4GB, 8K context

Name: NuExtract 1.5 Smol
Author: numind

NuExtract 1.5 Smol is an open-source language model by numind. Features: 1.7b LLM, VRAM: 3.4GB, Context: 8K, License: mit, LLM Explorer Score: 0.16.

Base model:finetune:huggingfac... Base model:huggingfacetb/smoll... Llama Multilingual Region:us Safetensors

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

NuExtract 1.5 Smol Parameters and Internals

Model Type

text generation, information extraction

Use Cases

Primary Use Cases:

Structured information extraction

Additional Notes

Designed to prioritize pure extraction; inputs should be structured accordingly.

Supported Languages

English (fluent), Multilingual (supported)

Training Details

Methodology:

Fine-tuning of Hugging Face's SmolLM2-1.7B

Input Output

Input Format:

<|input|>\n### Template:\n{template}\n### Text:\n{text}\n\n<|output|>

Accepted Modalities:

text

Output Format:

Structured JSON as per the template.

Performance Tips:

Use a JSON template for structured extraction.

LLM Name	NuExtract 1.5 Smol
Repository 🤗	https://huggingface.co/numind/NuExtract-1.5-smol
Base Model(s)	HuggingFaceTB/SmolLM2-1.7B HuggingFaceTB/SmolLM2-1.7B
Model Size	1.7b
Required VRAM	3.4 GB
Updated	2026-07-30
Maintainer	numind
Model Type	llama
Model Files	3.4 GB
Model Architecture	LlamaForCausalLM
License	mit
Context Length	8192
Model Max Length	8192
Transformers Version	4.45.2
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	49152
Torch Data Type	bfloat16

Rank the NuExtract 1.5 Smol 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 Smol

Model	Likes	Downloads	VRAM
NuExtract 1.5 Smol GGUF	7	144	0 GB

Best Alternatives to NuExtract 1.5 Smol

Best Alternatives	Context / RAM	Downloads	Likes
...FT Tulu3 Decontaminated Masked	16K / 3.4 GB	342	0
...B 16K SFT Tulu3 Decontaminated	16K / 3.4 GB	146	0
SmolLM2 1.7B 16K	16K / 3.4 GB	12	0
SmolLM2 1.7B Instruct 16K	16K / 3.4 GB	103	10
SmolLM2 1.7B Instruct	8K / 3.4 GB	154013	742
SmolLM2 1.7B Instruct	8K / 3.4 GB	4909	6
Yoru	8K / 3.4 GB	309	0
Augmented B933f090bb558b88	8K / 3.4 GB	574	0
...FT Tulu3 Decontaminated Masked	8K / 3.4 GB	274	0
Banglish Companion	8K / 6.8 GB	1254	0

Note: green Score (e.g. "73.2") means that the model is better than numind/NuExtract-1.5-smol.