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

Llama 30B Int4 by elinas

 »  All LLMs  »  elinas  »  Llama 30B Int4   URL Share it on

  17   
  Autotrain compatible   Endpoints compatible   Llama   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/elinas/llama-30b-int4 

Llama 30B Int4 Benchmarks

LLME Score: 0.07352
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 30B Int4 (elinas/llama-30b-int4)
🌟 Advertise your project 🚀

Llama 30B Int4 Parameters and Internals

Model Type 
auto-regressive, language model
Use Cases 
Areas:
research
Applications:
question answering, natural language understanding, reading comprehension
Primary Use Cases:
research on large language models, evaluation and mitigation of biases, developing improvement techniques
Limitations:
further risk evaluation required, not trained with human feedback, may generate harmful content
Additional Notes 
Instruction tuned, converted to int4 via GPTQ method.
Supported Languages 
en (excellent), fr (good), es (good), de (good), ru (average), zh (average)
Training Details 
Data Sources:
CCNet, C4, GitHub, Wikipedia, Books, ArXiv, Stack Exchange
Data Volume:
1.4 trillion tokens
Training Time:
December 2022 - February 2023
Model Architecture:
Transformer
Safety Evaluation 
Methodologies:
RAI datasets
Risk Categories:
gender, religion, race/Color, sexual orientation, age, nationality, disability, physical appearance, socioeconomic status
Ethical Considerations:
Data collected mostly from the Web, contains offensive, harmful, and biased content.
Responsible Ai Considerations 
Fairness:
Bias evaluation using RAI datasets for different categories like gender, religion, race, etc.
Transparency:
Data filtered using Kneser-Ney language model and fastText linear classifier based on proximity to Wikipedia.
Mitigation Strategies:
Filtered data based on proximity to Wikipedia text.
Input Output 
Input Format:
Instruction and response format
Accepted Modalities:
text
Performance Tips:
For deterministic results, turn off sampling; set specific sampler settings for better performance.
LLM NameLlama 30B Int4
Repository 🤗https://huggingface.co/elinas/llama-30b-int4 
Model Size30b
Required VRAM17 GB
Updated2025-09-20
Maintainerelinas
Model Typellama
Model Files  17.0 GB
Model ArchitectureLLaMAForCausalLM
Licenseother
Transformers Version4.27.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Llama 30B Int4

Best Alternatives
Context / RAM
Downloads
Likes
Llama 30B0K / 58.5 GB240
Llama 30B Int40K / 17 GB182
Llama 30B 3bit Gr1280K / 14 GB114
Note: green Score (e.g. "73.2") means that the model is better than elinas/llama-30b-int4.

Rank the Llama 30B Int4 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? 51483 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