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

Meta Llama 3 15B Instruct by win10

 »  All LLMs  »  win10  »  Meta Llama 3 15B Instruct   URL Share it on

  4   

Meta Llama 3 15B Instruct is an open-source language model by win10. Features: 15b LLM, VRAM: 23.9GB, Context: 8K, License: llama3, Instruction-Based, Merged, HF Score: 58.2, LLM Explorer Score: 0.16, Arc: 56, HellaSwag: 74.6, MMLU: 67.3, TruthfulQA: 53, WinoGrande: 74.5, GSM8K: 23.7.

  Merged Model   Conversational   En   Endpoints compatible   Instruct   Llama   Llama-3   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/win10/Meta-Llama-3-15B-Instruct 

Meta Llama 3 15B Instruct Benchmarks

ARC: 55.97 vs 96.7 (so35)-42.1%
HellaSwag: 74.63 vs 95.3 (gpt4)-21.7%
MMLU: 67.3 vs 88.3 (so35)-23.8%
TruthfulQA: 53 vs 59 (gpt4)-10.2%
WinoGrande: 74.51 vs 87.5 (gpt4)-14.8%
GSM8K: 23.65 vs 96.4 (so35)-75.5%
LLME Score: 0.15556
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 15B Instruct (win10/Meta-Llama-3-15B-Instruct)
🌟 Advertise your project 🚀

Meta Llama 3 15B Instruct Parameters and Internals

Model Type 
text generation
Additional Notes 
This model was created by merging pre-trained language models using the passthrough merge method and slice configuration as detailed in the YAML configuration. It uses bfloat16 data type.
LLM NameMeta Llama 3 15B Instruct
Repository 🤗https://huggingface.co/win10/Meta-Llama-3-15B-Instruct 
Merged ModelYes
Model Size15b
Required VRAM23.9 GB
Updated2026-04-04
Maintainerwin10
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-5   5.0 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.1 GB: 5-of-5
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Meta Llama 3 15B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Hamanasu 15B Instruct16K / 29.4 GB4739
L3 Aethora 15B V28K / 30.1 GB2242
OpenCrystal 15B L3 V38K / 30 GB1310
OpenCrystal L3 15B V2.18K / 30 GB35
OpenCrystal 15B L3 V28K / 30 GB36
Llama 3 15B Instruct Ft V28K / 30.1 GB74
Llama 3 15B Instruct Zeroed Ft8K / 30.1 GB52
L3 Aethora 15B V28K / 30.1 GB2644
LLaMa 3 Stheno V3.2 15B8K / 30 GB175
L3 NA Aethora 15B8K / 30.1 GB93
Note: green Score (e.g. "73.2") means that the model is better than win10/Meta-Llama-3-15B-Instruct.

Rank the Meta Llama 3 15B Instruct 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