ReasoningCore 3B 0 by EpistemeAI

 »  All LLMs  »  EpistemeAI  »  ReasoningCore 3B 0   URL Share it on

ReasoningCore 3B 0 is an open-source language model by EpistemeAI. Features: 3b LLM, VRAM: 6.5GB, Context: 128K, License: llama3.2, Quantized, Instruction-Based, LLM Explorer Score: 0.23.

  4bit Base model:finetune:unsloth/ll... Base model:unsloth/llama-3.2-3...   Conversational   Dataset:openai/gsm8k   En   Endpoints compatible   Instruct   Llama   Model-index   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth

ReasoningCore 3B 0 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ReasoningCore 3B 0 (EpistemeAI/ReasoningCore-3B-0)

ReasoningCore 3B 0 Parameters and Internals

LLM NameReasoningCore 3B 0
Repository 🤗https://huggingface.co/EpistemeAI/ReasoningCore-3B-0 
Base Model(s)  unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit   unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit
Model Size3b
Required VRAM6.5 GB
Updated2026-08-02
MaintainerEpistemeAI
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   1.5 GB: 2-of-2   5.0 GB: 1-of-2   1.5 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.48.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to ReasoningCore 3B 0

Best Alternatives
Context / RAM
Downloads
Likes
Legal Llama3.2 3B Sft Id128K / 6.5 GB6330
...gabl Legal Chatbot Llama3.2 3B128K / 6.5 GB5280
Legal Chatbot Llama3.2 3B Id128K / 6.5 GB360
Llama 3.2 3B Legal Id Sft128K / 6.5 GB2360
Llama 3.2 3B Legal Id Instruct128K / 6.5 GB1090
Legal Chatbot Llama3.2 3B Id128K / 6.5 GB680
Llama3.2 3B Legal Asisten Sft128K / 6.5 GB730
Llama 3.2 3B Indonesian Alpaca128K / 6.5 GB600
...3.2 3B Alpaca Indonesian Legal128K / 6.5 GB600
...3.2 3B Alpaca Indonesian Legal128K / 6.5 GB370
Note: green Score (e.g. "73.2") means that the model is better than EpistemeAI/ReasoningCore-3B-0.

Rank the ReasoningCore 3B 0 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? 55556 in total.

Our Social Media →  
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a