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

SmolLM2 1.7B by HuggingFaceTB

 »  All LLMs  »  HuggingFaceTB  »  SmolLM2 1.7B   URL Share it on

  134726   

SmolLM2 1.7B is an open-source language model by HuggingFaceTB. Features: 1.7b LLM, VRAM: 3.4GB, Context: 8K, License: apache-2.0, LLM Explorer Score: 0.29.

  Arxiv:2502.02737   Deploy:azure   En   Endpoints compatible   Llama   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B 

SmolLM2 1.7B Benchmarks

MMLU Pro: 12.64
GPQA: 3.91
MUSR: 4.6
BBH: 9.3
IFEval: 24.4 vs 88 (so35)-72.3%
MATH Lvl 5: 2.64
LLME Score: 0.28737
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SmolLM2 1.7B (HuggingFaceTB/SmolLM2-1.7B)
🌟 Advertise your project 🚀

SmolLM2 1.7B Parameters and Internals

Model Type 
language model
Use Cases 
Areas:
text rewriting, summarization, function calling
Applications:
research, commercial applications
Limitations:
Primarily understands and generates content in English., Generated content may not be factually accurate, logically consistent, or free from biases., Should be used as assistive tools rather than definitive sources of information.
Considerations:
Users should verify important information and critically evaluate any generated content.
Additional Notes 
The instruct version of the model is tuned to support tasks beyond standard language modeling.
Supported Languages 
en (primary)
Training Details 
Data Sources:
FineWeb-Edu, DCLM, The Stack, new mathematics dataset, coding dataset
Data Volume:
11 trillion tokens
Methodology:
Supervised fine-tuning (SFT), Direct Preference Optimization (DPO)
Hardware Used:
256 H100 GPUs
Model Architecture:
Transformer decoder
Input Output 
Accepted Modalities:
text
Performance Tips:
None specified.
LLM NameSmolLM2 1.7B
Repository 🤗https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B 
Model Size1.7b
Required VRAM3.4 GB
Updated2026-04-02
MaintainerHuggingFaceTB
Model Typellama
Model Files  3.4 GB
Supported Languagesen
Context Length8k
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassGPT2Tokenizer
Vocabulary Size49152
Torch Data Typebfloat16

Quantized Models of the SmolLM2 1.7B

Model
Likes
Downloads
VRAM
SmolTulu 1.7B Instruct13393 GB
SmolLM2 1.7B Bnb 4bit3861 GB

Best Alternatives to SmolLM2 1.7B

Best Alternatives
Context / RAM
Downloads
Likes
SmolLM2 1.7B Instruct 16K16K / 3.4 GB44910
SmolLM2 1.7B Instruct8K / 3.4 GB104194724
...ygnis Alpha 1.7B V0.1 Instruct8K / 3.4 GB5222
SmolLM2 1.7B Instruct8K / 3.4 GB18534
SmolTulu 1.7B Reinforced8K / 3.4 GB105
SmolLM2 1.7 Persona8K / 3.5 GB110
Penny 1.7B8K / 6.9 GB824
Smollm2 1.7B Base8K / 3.4 GB250
Superthoughts Lite V18K / 3.4 GB123
... 1.7B Smoltalk Stratified 100k8K / 3.4 GB60
Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceTB/SmolLM2-1.7B.

Rank the SmolLM2 1.7B 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? 52721 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