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 GPTQ by TheBloke

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

  7   

ARIA 70B V2 GPTQ is an open-source language model by TheBloke. Features: 70b LLM, VRAM: 35.3GB, Context: 4K, License: llama2, Quantized, LLM Explorer Score: 0.1.

  Arxiv:2307.09288   4-bit Base model:faradaylab/aria-70b... Base model:quantized:faradayla...   Code   Data   Education   En   Facebook   Fr   Gptq   Languages   Llama   Meta   Openassistant   Pytorch   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/ARIA-70B-V2-GPTQ 

ARIA 70B V2 GPTQ Benchmarks

LLME Score: 0.09551
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 GPTQ (TheBloke/ARIA-70B-V2-GPTQ)
🌟 Advertise your project 🚀

ARIA 70B V2 GPTQ Parameters and Internals

Model Type 
llama, text generation
Additional Notes 
ARIA is designed to be a helpful, respectful and honest assistant ensuring unbiased, safe, and correct responses.
Supported Languages 
fr (High proficiency), en (High proficiency)
Training Details 
Data Sources:
French Dataset from Enno
Data Volume:
50,000 high quality French tokens
Methodology:
Supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF)
Context Length:
6000
Training Time:
2 Days
Hardware Used:
NVIDIA A10G
Model Architecture:
Auto-regressive language model with optimized transformer architecture
Input Output 
Input Format:
Text only
Accepted Modalities:
text
Output Format:
Text generation
LLM NameARIA 70B V2 GPTQ
Repository 🤗https://huggingface.co/TheBloke/ARIA-70B-V2-GPTQ 
Model NameARIA 70B V2
Model CreatorFaradaylab
Base Model(s)  ARIA 70B V2   Faradaylab/ARIA-70B-V2
Model Size70b
Required VRAM35.3 GB
Updated2026-03-29
MaintainerTheBloke
Model Typellama
Model Files  35.3 GB
Supported Languagesfr en
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to ARIA 70B V2 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB3246
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB250
...ama 3.1 70B Instruct Gptq 4bit128K / 39.9 GB244
Opus V1.2 70B Marlin32K / 36.4 GB50
MoMo 70B Lora 1.8.6 DPO GPTQ32K / 41.3 GB111
MoMo 70B Lora 1.8.4 DPO GPTQ32K / 41.3 GB21
Tess 70B V1.6 Marlin31K / 36.3 GB71
Miqu 1 70B Sf GPTQ31K / 36.7 GB46510
Midnight Miqu 70B V1.5 GPTQ32G31K / 40.7 GB274
...Midnight Miqu 70B V1.0 GPTQ32G31K / 40.7 GB92
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/ARIA-70B-V2-GPTQ.

Rank the ARIA 70B V2 GPTQ 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