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

HRA Non Instruct Merged by rakdey

 »  All LLMs  »  rakdey  »  HRA Non Instruct Merged   URL Share it on

  46   

HRA Non Instruct Merged is an open-source language model by rakdey. Features: 1b LLM, VRAM: 2.5GB, Context: 128K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.29.

  4bit   En   Endpoints compatible   Instruct   Llama   Quantized   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/rakdey/HRA-Non-Instruct-Merged 

HRA Non Instruct Merged Benchmarks

LLME Score: 0.28778
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
HRA Non Instruct Merged (rakdey/HRA-Non-Instruct-Merged)
🌟 Advertise your project 🚀

HRA Non Instruct Merged Parameters and Internals

LLM NameHRA Non Instruct Merged
Repository 🤗https://huggingface.co/rakdey/HRA-Non-Instruct-Merged 
Base Model(s)  unsloth/llama-3.2-1b-unsloth-bnb-4bit   unsloth/llama-3.2-1b-unsloth-bnb-4bit
Model Size1b
Required VRAM2.5 GB
Updated2026-07-19
Maintainerrakdey
Model Typellama
Instruction-BasedYes
Model Files  2.5 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to HRA Non Instruct Merged

Best Alternatives
Context / RAM
Downloads
Likes
... Fable5 V2 Thinking OptiQ 4bit128K / 0.9 GB4212
Llama 3 8B Legal Chatbot Id128K / 2.5 GB7440
...lama 3.2 1B Legal Id Finetuned128K / 2.5 GB2670
Llama3.2 1B HAREM128K / 2.5 GB4110
Diqie123128K / 2.5 GB1750
CodeNexus128K / 2.5 GB440
...2 1B Instruct Unsloth Bnb 4bit128K / 1.1 GB754684
Llama 3.2 1B Instruct 4bit128K / 0.7 GB4986820
Llama 3.2 1B Instruct Bnb 4bit128K / 1 GB3633322
Orca Mini V9 5 1B Instruct128K / 2.5 GB234
Note: green Score (e.g. "73.2") means that the model is better than rakdey/HRA-Non-Instruct-Merged.

Rank the HRA Non Instruct Merged 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? 55234 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