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

Astralis 4x34B by Weyaxi

 »  All LLMs  »  Weyaxi  »  Astralis 4x34B   URL Share it on

  1674   
  Autotrain compatible   Conversational   Endpoints compatible   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow   Yi
Model Card on HF 🤗: https://huggingface.co/Weyaxi/Astralis-4x34B 

Astralis 4x34B Benchmarks

ARC: 69.71 vs 96.7 (so35)-27.9%
HellaSwag: 85.17 vs 95.3 (gpt4)-10.6%
MMLU: 77.24 vs 88.3 (so35)-12.5%
TruthfulQA: 63.55 vs 59 (gpt4)7.7%
WinoGrande: 84.14 vs 87.5 (gpt4)-3.8%
GSM8K: 71.65 vs 96.4 (so35)-25.7%
LLME Score: 0.15782
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Astralis 4x34B (Weyaxi/Astralis-4x34B)
🌟 Advertise your project 🚀

Astralis 4x34B Parameters and Internals

Model Type 
multimodal, Mixture of Experts (MoE)
Additional Notes 
More details coming soon.
LLM NameAstralis 4x34B
Repository 🤗https://huggingface.co/Weyaxi/Astralis-4x34B 
Model Size113.7b
Required VRAM227.7 GB
Updated2025-08-21
MaintainerWeyaxi
Model Typemixtral
Model Files  9.8 GB: 1-of-23   10.0 GB: 2-of-23   10.0 GB: 3-of-23   10.0 GB: 4-of-23   10.0 GB: 5-of-23   10.0 GB: 6-of-23   10.0 GB: 7-of-23   10.0 GB: 8-of-23   10.0 GB: 9-of-23   10.0 GB: 10-of-23   10.0 GB: 11-of-23   10.0 GB: 12-of-23   10.0 GB: 13-of-23   10.0 GB: 14-of-23   10.0 GB: 15-of-23   10.0 GB: 16-of-23   10.0 GB: 17-of-23   10.0 GB: 18-of-23   10.0 GB: 19-of-23   10.0 GB: 20-of-23   10.0 GB: 21-of-23   10.0 GB: 22-of-23   7.9 GB: 23-of-23
Model ArchitectureMixtralForCausalLM
Licenseother
Context Length200000
Model Max Length200000
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to Astralis 4x34B

Best Alternatives
Context / RAM
Downloads
Likes
Helion 4x34B195K / 227.7 GB173211
APUS XDAN 4.0 MoE V232K / 227.6 GB50
Note: green Score (e.g. "73.2") means that the model is better than Weyaxi/Astralis-4x34B.

Rank the Astralis 4x34B 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? 50804 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 v20241124
  Support LLM Explorer