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

Llama 3.2 3B by meta-llama

 »  All LLMs  »  meta-llama  »  Llama 3.2 3B   URL Share it on

  616308   

Llama 3.2 3B is an open-source language model by meta-llama. Features: 3b LLM, VRAM: 6.5GB, Context: 128K, License: llama3.2, LLM Explorer Score: 0.35.

  Arxiv:2204.05149   Arxiv:2405.16406   Autotrain compatible   De   En   Endpoints compatible   Es   Facebook   Fr   Hi   It   Llama   Llama-3   Meta   Pt   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Th
Model Card on HF 🤗: https://huggingface.co/meta-llama/Llama-3.2-3B 

Llama 3.2 3B Benchmarks

MMLU Pro: 16.53
GPQA: 2.35
MUSR: 3.81
BBH: 14.23
IFEval: 13.37 vs 88 (so35)-84.8%
MATH Lvl 5: 1.89
LLME Score: 0.3507
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3.2 3B (meta-llama/Llama-3.2-3B)
🌟 Advertise your project 🚀

Llama 3.2 3B Parameters and Internals

Model Type 
text generation, text summarization, multilingual
Use Cases 
Areas:
commercial, research
Applications:
knowledge retrieval, summarization, writing assistants, query and prompt rewriting
Primary Use Cases:
assistant chat, agentic applications
Limitations:
Use beyond supported languages without compliance with license, Violation of Acceptable Use Policy, Illegal activities
Considerations:
Encourage responsible use.
Additional Notes 
Initial release for commercial and research purposes.
Supported Languages 
en (English), de (German), fr (French), it (Italian), pt (Portuguese), hi (Hindi), es (Spanish), th (Thai)
Training Details 
Data Volume:
9 trillion tokens
Methodology:
Supervised Fine-Tuning (SFT), Rejection Sampling (RS), Direct Preference Optimization (DPO).
Context Length:
128000
Training Time:
916k GPU hours
Hardware Used:
H100-80GB GPUs
Model Architecture:
Optimized transformer architecture with autoregressive language model.
Safety Evaluation 
Methodologies:
Red teaming, Safety fine-tuning
Findings:
N/A
Risk Categories:
CBRNE
Responsible Ai Considerations 
Mitigation Strategies:
System safeguards include Llama Guard, Prompt Guard, and Code Shield.
Input Output 
Input Format:
Multilingual Text
Accepted Modalities:
text
Output Format:
Multilingual Text and code
LLM NameLlama 3.2 3B
Repository 🤗https://huggingface.co/meta-llama/Llama-3.2-3B 
Model Size3b
Required VRAM6.5 GB
Updated2025-09-23
Maintainermeta-llama
Model Typellama
Model Files  5.0 GB: 1-of-2   1.5 GB: 2-of-2
Supported Languagesen de fr it pt hi es th
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.45.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Quantized Models of the Llama 3.2 3B

Model
Likes
Downloads
VRAM
Teuta211536 GB
Llama 3.2 3B Bnb 4bit20106152 GB
Llm 3 2 Flux Prompt1415296 GB
Llama 3.2 3B COT2946 GB
Llama 3.2 3B GGUF2662 GB

Best Alternatives to Llama 3.2 3B

Best Alternatives
Context / RAM
Downloads
Likes
ISA 03 Mini 3B Hybrid Preview256K / 6.5 GB8514
Llama 3.2 3B Instruct128K / 6.5 GB16749181724
Hermes 3 Llama 3.2 3B128K / 6.5 GB5468172
Llama 3.2 3B Instruct128K / 6.5 GB42213275
Llama 3.2 3B RP Toxic Fuse128K / 6.4 GB42
Calme 3.1 Llamaloi 3B128K / 10.6 GB21161
DeepSeek R1 Distill Llama 3B128K / 6.5 GB14116
Orpheus 3B 0.1 Ft128K / 6.6 GB2304412
Jajuka 3B128K / 6.4 GB262
JAJUKA WEWILLNEVERFORGETYOU 3B128K / 6.4 GB243
Note: green Score (e.g. "73.2") means that the model is better than meta-llama/Llama-3.2-3B.

Rank the Llama 3.2 3B 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? 51638 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