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

Llama 3.2 3B 8bit by mlx-community

 »  All LLMs  »  mlx-community  »  Llama 3.2 3B 8bit   URL Share it on

  131   

Llama 3.2 3B 8bit is an open-source language model by mlx-community. Features: 3b LLM, VRAM: 3.4GB, Context: 128K, License: llama3.2, Quantized, LLM Explorer Score: 0.15.

  8bit   De   En   Endpoints compatible   Es   Facebook   Fr   Hi   It   Llama   Llama-3   Meta   Mlx   Pt   Pytorch   Quantized   Region:us   Safetensors   Th
Model Card on HF 🤗: https://huggingface.co/mlx-community/Llama-3.2-3B-8bit 

Llama 3.2 3B 8bit Benchmarks

LLME Score: 0.15486
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 8bit (mlx-community/Llama-3.2-3B-8bit)
🌟 Advertise your project 🚀

Llama 3.2 3B 8bit Parameters and Internals

Model Type 
text generation
Additional Notes 
Converted to MLX format from meta-llama/Llama-3.2-3B using mlx-lm version 0.17.1.
Supported Languages 
en (full), de (full), fr (full), it (full), pt (full), hi (full), es (full), th (full)
Input Output 
Accepted Modalities:
text
Output Format:
text
LLM NameLlama 3.2 3B 8bit
Repository 🤗https://huggingface.co/mlx-community/Llama-3.2-3B-8bit 
Model Size3b
Required VRAM3.4 GB
Updated2026-05-20
Maintainermlx-community
Model Typellama
Model Files  3.4 GB
Supported Languagesen de fr it pt hi es th
Quantization Type8bit
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.45.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3.2 3B 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Nanbeige4.1 3B 8bit256K / 4.2 GB25514
Nanbeige4.1 3B Heretic 8bit256K / 4.2 GB442
Llama3.2 3B Base Math128K / 6.5 GB5590
Llama3.2 3B Base Code128K / 6.5 GB4750
Llama32 3B En Emo 2000 Stp128K / 2.2 GB950
Llama32 3B En Emo 300 Stp128K / 2.2 GB90
Llama32 3B En Emo 1000 Stp128K / 2.2 GB60
Llama32 3B En Emo 5000 Stp128K / 2.2 GB90
...ngCore 3B Instruct R01 Reflect128K / 6.5 GB01
...2 3B Instruct Unsloth Bnb 4bit128K / 2.4 GB9267110
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Llama-3.2-3B-8bit.

Rank the Llama 3.2 3B 8bit 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? 53999 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