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 Bespoke Thought by bunnycore

 »  All LLMs  »  bunnycore  »  Llama 3.2 3B Bespoke Thought   URL Share it on

  45   
  Merged Model   Autotrain compatible Base model:bunnycore/llama-3.2... Base model:unsloth/llama-3.2-3...   Conversational   Endpoints compatible   Instruct   Llama   Lora   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/bunnycore/Llama-3.2-3B-Bespoke-Thought 

Llama 3.2 3B Bespoke Thought Benchmarks

MMLU Pro: 23.44
GPQA: 2.13
MUSR: 2.38
BBH: 22.52
IFEval: 41.13 vs 88 (so35)-53.3%
MATH Lvl 5: 16.47
LLME Score: 0.30578
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 Bespoke Thought (bunnycore/Llama-3.2-3B-Bespoke-Thought)

Llama 3.2 3B Bespoke Thought Parameters and Internals

LLM NameLlama 3.2 3B Bespoke Thought
Repository 🤗https://huggingface.co/bunnycore/Llama-3.2-3B-Bespoke-Thought 
Base Model(s)  unsloth/Llama-3.2-3B-Instruct   bunnycore/Llama-3.2-3B-R1-lora   unsloth/Llama-3.2-3B-Instruct   bunnycore/Llama-3.2-3B-R1-lora
Merged ModelYes
Model Size3b
Required VRAM6.4 GB
Updated2025-03-12
Maintainerbunnycore
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   1.4 GB: 2-of-2
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.48.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
LoRA ModelYes
Torch Data Typebfloat16

Best Alternatives to Llama 3.2 3B Bespoke Thought

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct128K / 6.5 GB30134691190
DeepSeek R1 Distill Llama 3B128K / 6.5 GB7369
Llama 3.2 3B ToxicKod128K / 6.4 GB322
Zeitgeist 3B V1128K / 6.5 GB1055
Eximius Persona 5B128K / 11.6 GB4534
ReasoningCore 3B T1 1128K / 6.5 GB1090
...eflection L3.2 JametMiniMix 3B128K / 6.4 GB1711
...0 3B Instruct R01 Reflect Math128K / 6.5 GB170
...3.2 Rabbit Ko 3B Instruct 2412128K / 6.5 GB11694
...lama 3.2 Rabbit Ko 3B Instruct128K / 6.5 GB22068
Note: green Score (e.g. "73.2") means that the model is better than bunnycore/Llama-3.2-3B-Bespoke-Thought.

Rank the Llama 3.2 3B Bespoke Thought 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? 44887 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 v20241227
  Support LLM Explorer