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

DynaGuard 4B by tomg-group-umd

 »  All LLMs  »  tomg-group-umd  »  DynaGuard 4B   URL Share it on

  207   
  Arxiv:2509.02563   Autotrain compatible Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-4b   Conversational Dataset:tomg-group-umd/dynaben...   Dynaguard   En   Endpoints compatible   Guardrail   Moderation   Qwen3   Region:us   Safetensors   Safety   Sharded   Tensorflow   Umd
Model Card on HF 🤗: https://huggingface.co/tomg-group-umd/DynaGuard-4B 

DynaGuard 4B Benchmarks

LLME Score: 0.25432
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DynaGuard 4B (tomg-group-umd/DynaGuard-4B)
🌟 Advertise your project 🚀

DynaGuard 4B Parameters and Internals

LLM NameDynaGuard 4B
Repository 🤗https://huggingface.co/tomg-group-umd/DynaGuard-4B 
Base Model(s)  Qwen/Qwen3-4B   Qwen/Qwen3-4B
Model Size4b
Required VRAM8.8 GB
Updated2025-09-23
Maintainertomg-group-umd
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.8 GB: 2-of-2
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to DynaGuard 4B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B Instruct 2507256K / 8.1 GB1473674320
Qwen3 4B Thinking 2507256K / 8.1 GB315603426
Jan V1 4B256K / 8.1 GB5605336
Qwen3 4B Thinking 2507 FP8256K / 5.2 GB20887035
WEBGEN 4B Preview256K / 8.1 GB147680
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB4154231
Qwen3 4B Instruct 2507256K / 8.1 GB4428910
Qwen3 4B Thinking 2507256K / 8.1 GB101705
Jan V1.2509256K / 8.1 GB40528
DistilGPT OSS Qwen3 4B256K / 8.1 GB22417
Note: green Score (e.g. "73.2") means that the model is better than tomg-group-umd/DynaGuard-4B.

Rank the DynaGuard 4B 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? 51544 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