LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

OpenAssistant Llama 30B 4bit by MetaIX

 »  All LLMs  »  MetaIX  »  OpenAssistant Llama 30B 4bit   URL Share it on

  19   
  4bit   Autotrain compatible   Endpoints compatible   Ggml   Llama   Pytorch   Q4   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/MetaIX/OpenAssistant-Llama-30b-4bit 

OpenAssistant Llama 30B 4bit Benchmarks

LLME Score: 0.09166
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
OpenAssistant Llama 30B 4bit (MetaIX/OpenAssistant-Llama-30b-4bit)

OpenAssistant Llama 30B 4bit Parameters and Internals

Model Type 
text generation
Training Details 
Data Sources:
Open Assistant dataset
Methodology:
native fine-tune
Release Notes 
Version:
latest
Date:
04.29.2023
Notes:
Updated to the latest fine-tune by Open Assistant oasst-sft-7-llama-30b-xor.
Version:
latest
Date:
05.27.2023
Notes:
Updated the GGML quantizations to be compatible with the latest version of llamacpp (again).
LLM NameOpenAssistant Llama 30B 4bit
Repository 🤗https://huggingface.co/MetaIX/OpenAssistant-Llama-30b-4bit 
Model Size30b
Required VRAM16.9 GB
Updated2025-06-02
MaintainerMetaIX
Model Typellama
Model Files  18.1 GB   16.9 GB   20.3 GB   22.4 GB   24.4 GB
GGML QuantizationYes
Quantization Typeggml|q4|4bit
Model ArchitectureLlamaForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.29.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32016
Torch Data Typefloat16

Best Alternatives to OpenAssistant Llama 30B 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Tamillama Tiny 30m2K / 0.1 GB15415
GPT4 X Alpasta 30B 4bit2K / 16.9 GB1868
Alpacino30b2K / 64.1 GB2568
Bluemoonrp 30B2K / 17.5 GB2024
GPT4 X Alpaca 30B 4bit2K / 16.9 GB13162
Tenebra 30B Alpha01 FP1616K / 65 GB18339
...nebra 30B Alpha01 EXL2 2 80bpw16K / 11.9 GB221
...nebra 30B Alpha01 EXL2 2 50bpw16K / 10.7 GB190
Tenebra 30B Alpha01 EXL2 3bpw16K / 12.7 GB140
Tenebra 30B Alpha01 3BIT16K / 12.9 GB190
Note: green Score (e.g. "73.2") means that the model is better than MetaIX/OpenAssistant-Llama-30b-4bit.

Rank the OpenAssistant Llama 30B 4bit 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? 47796 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