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

ARIA 70B V2 GGUF by TheBloke

 »  All LLMs  »  TheBloke  »  ARIA 70B V2 GGUF   URL Share it on

  85   

ARIA 70B V2 GGUF is an open-source language model by TheBloke. Features: 70b LLM, VRAM: 29.3GB, License: llama2, Quantized, LLM Explorer Score: 0.1.

  Arxiv:2307.09288 Base model:faradaylab/aria-70b... Base model:quantized:faradayla...   Code   Data   Education   En   Facebook   Fr   Gguf   Languages   Llama   Meta   Openassistant   Pytorch   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/ARIA-70B-V2-GGUF 

ARIA 70B V2 GGUF Benchmarks

LLME Score: 0.09662
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ARIA 70B V2 GGUF (TheBloke/ARIA-70B-V2-GGUF)
🌟 Advertise your project 🚀

ARIA 70B V2 GGUF Parameters and Internals

Model Type 
text-generation, auto-regressive, supervised fine-tuning, reinforcement learning with human feedback
Use Cases 
Areas:
text generation, research, commercial applications
Applications:
French language datasets, General dialogue-based applications
Primary Use Cases:
Dialogue generation, Data extraction from large files
Limitations:
Language understanding limited within the context length, Model might perform less accurately on topics outside the training languages
Additional Notes 
Rope scaling can be applied for handling larger files/contexts.
Supported Languages 
fr (French), en (English)
Training Details 
Data Sources:
French Dataset from Enno, Own dataset
Data Volume:
50,000 rows
Methodology:
Supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF)
Context Length:
6000
Training Time:
2 Days
Hardware Used:
NVIDIA A10G GPUS, Amazon Cloud Sagemaker
Model Architecture:
Auto-regressive language model with transformer architecture
Responsible Ai Considerations 
Fairness:
Model aims to ensure unbiased and positive responses.
Transparency:
Model's safety and help suggestions are transparent about non-factually coherent inputs.
Accountability:
Not explicitly stated
Mitigation Strategies:
Model is trained to provide socially unbiased responses.
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Activate rope scaling for increased context length handling
LLM NameARIA 70B V2 GGUF
Repository 🤗https://huggingface.co/TheBloke/ARIA-70B-V2-GGUF 
Model NameARIA 70B V2
Model CreatorFaradaylab
Base Model(s)  ARIA 70B V2   Faradaylab/ARIA-70B-V2
Model Size70b
Required VRAM29.3 GB
Updated2026-03-15
MaintainerTheBloke
Model Typellama
Model Files  29.3 GB   36.1 GB   33.2 GB   29.9 GB   38.9 GB   41.4 GB   39.1 GB   47.5 GB   48.8 GB   47.5 GB
Supported Languagesfr en
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licensellama2

Best Alternatives to ARIA 70B V2 GGUF

Best Alternatives
Context / RAM
Downloads
Likes
...us Qwen3 R1 Llama Distill GGUF0K / 0.8 GB2362
...gekit Passthrough Yqhuxcv GGUF0K / 16.9 GB1100
KafkaLM 70B German V0.1 GGUF0K / 25.5 GB240256
CodeLlama 70B Instruct GGUF0K / 25.5 GB215960
CodeLlama 70B Python GGUF0K / 25.5 GB159644
Meta Llama 3 70B Instruct GGUF0K / 26.4 GB1334
DAD Model V2 70B Q40K / 42.5 GB80
CodeLlama 70B Hf GGUF0K / 25.5 GB55842
Swallow 70B Instruct GGUF0K / 29.4 GB15509
Llama 2 70B Guanaco QLoRA GGUF0K / 29.3 GB190
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/ARIA-70B-V2-GGUF.

Rank the ARIA 70B V2 GGUF 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? 52392 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