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

Mistral NeMo Minitron 8B Base by nvidia

 »  All LLMs  »  nvidia  »  Mistral NeMo Minitron 8B Base   URL Share it on

  3140   

Mistral NeMo Minitron 8B Base is an open-source language model by nvidia. Features: 8b LLM, VRAM: 16.8GB, Context: 8K, License: other, LLM Explorer Score: 0.26.

  Arxiv:2009.03300   Arxiv:2407.14679   Arxiv:2408.11796   Deploy:azure   Endpoints compatible   Mistral   Nemo   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/Mistral-NeMo-Minitron-8B-Base 

Mistral NeMo Minitron 8B Base Benchmarks

MMLU Pro: 31.06
GPQA: 10.07
MUSR: 8.94
BBH: 31.82
IFEval: 19.46 vs 88 (so35)-77.9%
MATH Lvl 5: 4.83
LLME Score: 0.25721
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral NeMo Minitron 8B Base (nvidia/Mistral-NeMo-Minitron-8B-Base)
🌟 Advertise your project 🚀

Mistral NeMo Minitron 8B Base Parameters and Internals

Model Type 
text-to-text, language model
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
natural language generation
Limitations:
May amplify societal biases and return toxic responses, Inaccurate or omitted key information in responses
Considerations:
Developers should work with internal teams to ensure the model meets industry and use case requirements.
Supported Languages 
English (high), multilingual (varied)
Training Details 
Data Sources:
webpages, dialogues, articles, legal documents, math texts, science literature, financial documents
Data Volume:
380 billion tokens
Methodology:
pruning and distillation
Context Length:
8000
Hardware Used:
NVIDIA A100
Model Architecture:
Transformer Decoder (Auto-Regressive Language Model)
Responsible Ai Considerations 
Fairness:
The model may reflect biases present in the training data.
Transparency:
Model architecture and training methodologies are described in the report.
Accountability:
Developers using the model should ensure it meets industry requirements and mitigates potential biases.
Mitigation Strategies:
Introduced QA and alignment style data for performance improvements.
Input Output 
Input Format:
String (1D)
Accepted Modalities:
text
Output Format:
String (1D)
Performance Tips:
Works well within 8k characters or less.
LLM NameMistral NeMo Minitron 8B Base
Repository 🤗https://huggingface.co/nvidia/Mistral-NeMo-Minitron-8B-Base 
Model Size8b
Required VRAM16.8 GB
Updated2026-03-11
Maintainernvidia
Model Typemistral
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   2.0 GB: 4-of-4
Model ArchitectureMistralForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Mistral NeMo Minitron 8B Base

Best Alternatives
Context / RAM
Downloads
Likes
...l 8B Instruct 2410 Abliterated32K / 16.1 GB3562
Ministral 8B Instruct 2410 HF32K / 32 GB2711
Ministrations 8B V132K / 16.1 GB924
Minerva 8B32K / 14.5 GB70
Ministral 8B Slerp32K / 29.2 GB70
The Omega Directive M 8B V1.032K / 16.1 GB309
Deeplm Mistral V0.1 8B Stage132K / 14.5 GB31
DeepOpus 1 8B Preview32K / 16.1 GB752
Forgotten Abomination 8B V2.232K / 16.1 GB32
DeepNeo 1 8B Preview32K / 16.1 GB632

Rank the Mistral NeMo Minitron 8B 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? 51633 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 v20241124
  Support LLM Explorer