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

Meta Llama 3 8B Fp8 by FriendliAI

 »  All LLMs  »  FriendliAI  »  Meta Llama 3 8B Fp8   URL Share it on

  9   
  8-bit   Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/meta-lla...   En   Facebook   Llama   Llama-3   Meta   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/FriendliAI/Meta-Llama-3-8B-fp8 

Meta Llama 3 8B Fp8 Benchmarks

LLME Score: 0.1471
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Meta Llama 3 8B Fp8 (FriendliAI/Meta-Llama-3-8B-fp8)
🌟 Advertise your project 🚀

Meta Llama 3 8B Fp8 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Commercial, Research
Applications:
Assistant-like chat, NLG tasks
Primary Use Cases:
Instruction tuning for dialogue
Limitations:
Only pre-trained in English; Fine-tuning required for additional languages.
Considerations:
Developers are advised to implement safety checks for their specific applications.
Additional Notes 
Quantized to FP8 by FriendliAI for efficiency.
Supported Languages 
en (full)
Training Details 
Data Sources:
A new mix of publicly available online data
Data Volume:
15T+ tokens
Methodology:
Pre-trained and instruction tuned using supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF)
Training Time:
Hardware Used:
H100-80GB GPUs
Model Architecture:
Transformer
Safety Evaluation 
Methodologies:
Red teaming, Adversarial evaluations
Findings:
Model showed safety improvements over predecessors
Risk Categories:
CBRNE threats, Cybersecurity, Child Safety
Ethical Considerations:
Focused on reducing harmful outputs and aligning with human preferences.
Responsible Ai Considerations 
Fairness:
Open approach for inclusive use cases; Developers encouraged to tailor for fairness.
Transparency:
Open community tools and resources available for evaluation.
Accountability:
Meta facilitates community feedback.
Mitigation Strategies:
Provides safeguards like Meta Llama Guard 2
Input Output 
Input Format:
Text
Accepted Modalities:
text
Output Format:
Generates text and code
Performance Tips:
Fine-tuning recommended for specific tasks.
Release Notes 
Version:
3
Date:
April 18, 2024
Notes:
Initial release of Llama 3 model family.
LLM NameMeta Llama 3 8B Fp8
Repository 🤗https://huggingface.co/FriendliAI/Meta-Llama-3-8B-fp8 
Model NameLlama 3 8B
Model CreatorMeta Llama 3
Base Model(s)  Meta Llama 3 8B   meta-llama/Meta-Llama-3-8B
Model Size8b
Required VRAM9.1 GB
Updated2025-09-23
MaintainerFriendliAI
Model Typellama
Model Files  9.1 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.40.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Quantized Models of the Meta Llama 3 8B Fp8

Model
Likes
Downloads
VRAM
Meta Llama 3 8B GPTQ511325 GB
Meta Llama 3 8B GPTQ055 GB
Meta Llama 3 8B GPTQ065 GB
Meta Llama 3 8B GPTQ055 GB
Meta Llama 3 8B 8bit5199 GB
Meta Llama 3 8B GPTQ055 GB

Best Alternatives to Meta Llama 3 8B Fp8

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB1531120
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
UltraLong Thinking4192K / 16.1 GB453
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB114215
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB714252
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...xis Bookwriter Llama3.1 8B Sft1048K / 16.1 GB404
Zero Llama 3.1 8B Beta61048K / 16.1 GB21
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB53
Note: green Score (e.g. "73.2") means that the model is better than FriendliAI/Meta-Llama-3-8B-fp8.

Rank the Meta Llama 3 8B Fp8 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? 51545 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