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 Instruct Bnb 4bit by unsloth

 »  All LLMs  »  unsloth  »  Llama 3.2 3B Instruct Bnb 4bit   URL Share it on

  211165   
  4-bit   4bit   Autotrain compatible Base model:meta-llama/llama-3.... Base model:quantized:meta-llam...   Bitsandbytes   Conversational   En   Endpoints compatible   Facebook   Instruct   Llama   Llama-3   Meta   Quantized   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-bnb-4bit 

Llama 3.2 3B Instruct Bnb 4bit Benchmarks

LLME Score: 0.35549
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 Bnb 4bit (unsloth/Llama-3.2-3B-Instruct-bnb-4bit)

Llama 3.2 3B Instruct Bnb 4bit Parameters and Internals

Model Type 
text generation
Additional Notes 
Future versions may be released that improve model capabilities and safety.
Supported Languages 
en (high), de (high), fr (high), it (high), pt (high), hi (high), es (high), th (high)
Training Details 
Methodology:
The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
Model Architecture:
Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture.
Input Output 
Input Format:
text in
Output Format:
text out
LLM NameLlama 3.2 3B Instruct Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-bnb-4bit 
Base Model(s)  meta-llama/Llama-3.2-3B-Instruct   meta-llama/Llama-3.2-3B-Instruct
Model Size3b
Required VRAM2.2 GB
Updated2024-12-21
Maintainerunsloth
Model Typellama
Instruction-BasedYes
Model Files  2.2 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.45.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Quantized Models of the Llama 3.2 3B Instruct Bnb 4bit

Model
Likes
Downloads
VRAM
FineTome Llama3.2 3B 10021386 GB
...Llama 3.2 3B Instruct Bnb 4bit1886 GB
Llama3.20387 GB
...3.2 3B SFT Medmcqa Triples Cot0396 GB
...ma3.2 3B SFT Medqa Triples Cot0356 GB

Best Alternatives to Llama 3.2 3B Instruct Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct 4bit128K / 1.8 GB21935720
Komodo Llama 3.2 3B V2 Fp16128K / 6.5 GB6415
Gladiator Mini Exp 1211 3B128K / 6.5 GB170
Reasoning Llama 3B V0.1128K / 6.5 GB3959
Llama 3.2 3B Overthinker128K / 6.5 GB16819
Llama Sentient 3.2 3B Instruct128K / 6.5 GB39410
Llama Magpie 3.2 3B Instruct128K / 6.5 GB1957
...truct Gptqmodel 4bit Vortex V3128K / 3.2 GB16124
Llama 3.2 3B Fluxed128K / 6.5 GB4600
Llama 3.2 3B Promptist Mini128K / 6.5 GB878
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Llama-3.2-3B-Instruct-bnb-4bit.

Rank the Llama 3.2 3B Instruct Bnb 4bit 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? 40013 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 v20241217
  Support LLM Explorer