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

Minitron 4B Base by nvidia

 »  All LLMs  »  nvidia  »  Minitron 4B Base   URL Share it on

  1333   
  Arxiv:2009.03300   Arxiv:2407.14679   Autotrain compatible   En   Endpoints compatible   Llama-3   Nemo   Nemotron   Nvidia   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/nvidia/Minitron-4B-Base 

Minitron 4B Base Benchmarks

MMLU Pro: 18
GPQA: 2.57
MUSR: 9.94
BBH: 17.22
IFEval: 22.18 vs 88 (so35)-74.8%
MATH Lvl 5: 1.96
LLME Score: 0.23402
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Minitron 4B Base (nvidia/Minitron-4B-Base)
🌟 Advertise your project 🚀

Minitron 4B Base Parameters and Internals

Model Type 
Transformer Decoder, auto-regressive language model
Use Cases 
Areas:
research, development
Limitations:
amplifies biases, can generate toxic responses, may produce inaccurate or undesirable text
Considerations:
Work with internal model team to ensure model meets industry requirements and addresses unforeseen misuse.
Supported Languages 
en (basic proficiency), multilingual (basic proficiency)
Training Details 
Data Sources:
webpages, dialogue, articles, other written materials
Data Volume:
94 billion tokens
Methodology:
pruning and knowledge distillation
Model Architecture:
Transformer Decoder
Input Output 
Input Format:
String
Accepted Modalities:
Text
Output Format:
String
Performance Tips:
Load the model using TensorRT-LLM on supported hardware with CUDA and Torch settings for optimal performance.
LLM NameMinitron 4B Base
Repository 🤗https://huggingface.co/nvidia/Minitron-4B-Base 
Model Size4b
Required VRAM8.4 GB
Updated2025-09-23
Maintainernvidia
Model Typenemotron
Model Files  8.4 GB
Supported Languagesen
Model ArchitectureNemotronForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.32.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Minitron 4B Base

Best Alternatives
Context / RAM
Downloads
Likes
Nemotron Mini 4B Instruct4K / 8.4 GB4159169
Nemotron Mini 4B Instruct4K / 16.7 GB60
...otron 4 Mini Hindi 4B Instruct4K / 16.7 GB50
Nemotron 4 Mini Hindi 4B Base4K / 16.7 GB60
...4B Intermediate Gliner En Exp44K / 8.4 GB1290
HindiNER 4B V1.04K / 8.4 GB80
...indi 4B Constraint Phase1 Exp14K / 8.4 GB310
...4B Intermediate Gliner En Exp34K / 8.4 GB60
...otron 4 Mini Hindi 4B Instruct4K / 8.4 GB60
Note: green Score (e.g. "73.2") means that the model is better than nvidia/Minitron-4B-Base.

Rank the Minitron 4B Base 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? 51544 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.
Release v20241124
  Support LLM Explorer