Llama 3.2 3B Instruct 4bit by mlx-community

 ยป  All LLMs  ยป  mlx-community  ยป  Llama 3.2 3B Instruct 4bit   URL Share it on

  4-bit   4bit   Autotrain compatible Base model:mlx-community/llama... Base model:quantized:mlx-commu...   Conversational   De   En   Endpoints compatible   Es   Facebook   Fr   Hi   Instruct   It   Llama   Llama-3   Meta   Mlx   Pt   Pytorch   Quantized   Region:us   Safetensors   Th

Llama 3.2 3B Instruct 4bit Benchmarks

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 Instruct 4bit (mlx-community/Llama-3.2-3B-Instruct-4bit)

Llama 3.2 3B Instruct 4bit Parameters and Internals

Model Type 
text-generation
Additional Notes 
Converted to MLX format
Supported Languages 
en (High), de (High), fr (High), it (High), pt (High), hi (High), es (High), th (High)
Input Output 
Input Format:
Text-based prompts
Accepted Modalities:
text
Output Format:
Text
LLM NameLlama 3.2 3B Instruct 4bit
Repository ๐Ÿค—https://huggingface.co/mlx-community/Llama-3.2-3B-Instruct-4bit 
Base Model(s)  mlx-community/Llama-3.2-3B-Instruct   mlx-community/Llama-3.2-3B-Instruct
Model Size3b
Required VRAM1.8 GB
Updated2025-03-12
Maintainermlx-community
Model Typellama
Instruction-BasedYes
Model Files  1.8 GB
Supported Languagesen de fr it pt hi es th
Quantization Type4bit
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 Instruct 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...2 3B Instruct Unsloth Bnb 4bit128K / 2.4 GB2653186
Llama32 3B En Emo 2000 Stp128K / 2.2 GB420
Llama32 3B En Emo 300 Stp128K / 2.2 GB300
ReasoningCore 3B 0128K / 6.5 GB2152
Llama32 3B En Emo 1000 Stp128K / 2.2 GB130
...ngCore 3B Instruct R01 Reflect128K / 6.5 GB281
Llama32 3B En Emo 5000 Stp128K / 2.2 GB130
Security Llama3.2 3B128K / 6.5 GB580
Llama 3.2 3B Unsloth Bnb 4bit128K / 2.4 GB266342
Llama32 3B En Emo V3128K / 2.2 GB670
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Llama-3.2-3B-Instruct-4bit.

Rank the Llama 3.2 3B Instruct 4bit Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 44887 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227