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

Astral 4B Preview by LucidityAI

 »  All LLMs  »  LucidityAI  »  Astral 4B Preview   URL Share it on

  21   
  Autotrain compatible   Chat   Code   Conversational Dataset:nvidia/acereason-1.1-s...   Endpoints compatible   Inference   Multimodal (if applicable)   Qwen3   Reasoning   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LucidityAI/Astral-4B-Preview 

Astral 4B Preview Benchmarks

LLME Score: 0.26731
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Astral 4B Preview (LucidityAI/Astral-4B-Preview)
🌟 Advertise your project 🚀

Astral 4B Preview Parameters and Internals

LLM NameAstral 4B Preview
Repository 🤗https://huggingface.co/LucidityAI/Astral-4B-Preview 
Base Model(s)  Qwen/Qwen3-4b-thinking-2507   Qwen/Qwen3-4b-thinking-2507
Model Size4b
Required VRAM8.1 GB
Updated2025-09-06
MaintainerLucidityAI
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.1 GB: 2-of-2
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.52.4
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Astral 4B Preview

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B Instruct 2507256K / 8.1 GB841718265
Qwen3 4B Thinking 2507256K / 8.1 GB196403344
Jan V1 4B256K / 8.1 GB11829323
WEBGEN 4B Preview256K / 8.1 GB34746
Qwen3 4B Thinking 2507 FP8256K / 5.2 GB16903727
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB2942627
Qwen3 4B Instruct 2507256K / 8.1 GB357368
...4B Thinking 2507 DAG Reasoning256K / 16.1 GB91984
Qwen3 4B Thinking 2507256K / 8.1 GB64383
Luna256K / 8.1 GB677
Note: green Score (e.g. "73.2") means that the model is better than LucidityAI/Astral-4B-Preview.

Rank the Astral 4B Preview 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? 51147 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