LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

NuExtract 1.5 Smol by numind

 »  All LLMs  »  numind  »  NuExtract 1.5 Smol   URL Share it on

  207   

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: 0.17.

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 Benchmarks

LLME Score: 0.16973
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NuExtract 1.5 Smol (numind/NuExtract-1.5-smol)
🌟 Advertise your project 🚀

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 NameNuExtract 1.5 Smol
Repository 🤗https://huggingface.co/numind/NuExtract-1.5-smol 
Base Model(s)  HuggingFaceTB/SmolLM2-1.7B   HuggingFaceTB/SmolLM2-1.7B
Model Size1.7b
Required VRAM3.4 GB
Updated2026-05-20
Maintainernumind
Model Typellama
Model Files  3.4 GB
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length8192
Model Max Length8192
Transformers Version4.45.2
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size49152
Torch Data Typebfloat16

Quantized Models of the NuExtract 1.5 Smol

Model
Likes
Downloads
VRAM
NuExtract 1.5 Smol GGUF7720 GB

Best Alternatives to NuExtract 1.5 Smol

Best Alternatives
Context / RAM
Downloads
Likes
...B 16K SFT Tulu3 Decontaminated16K / 3.4 GB1460
SmolLM2 1.7B Instruct 16K16K / 3.4 GB15710
SmolLM2 1.7B Instruct8K / 3.4 GB182834728
SmolLM2 1.7B Instruct8K / 3.4 GB17476
SmolLM2 1.7B8K / 3.4 GB100619150
...ygnis Alpha 1.7B V0.1 Instruct8K / 3.4 GB1702
SmolTulu 1.7B Reinforced8K / 3.4 GB115
SmolLM2 1.7 Persona8K / 3.5 GB970
Penny 1.7B8K / 6.9 GB17024
Smollm2 1.7B Base8K / 3.4 GB250
Note: green Score (e.g. "73.2") means that the model is better than numind/NuExtract-1.5-smol.

Rank the NuExtract 1.5 Smol Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 53999 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer