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

GRAM Qwen3 4B RewardModel by NiuTrans

 »  All LLMs  »  NiuTrans  »  GRAM Qwen3 4B RewardModel   URL Share it on

  13   
  Arxiv:2506.14175 Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-4b   En   Gram   Qwen3   Region:us   Reward   Rewardmodel   Rlhf   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/NiuTrans/GRAM-Qwen3-4B-RewardModel 

GRAM Qwen3 4B RewardModel Benchmarks

LLME Score: 0.25954
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
GRAM Qwen3 4B RewardModel (NiuTrans/GRAM-Qwen3-4B-RewardModel)
🌟 Advertise your project 🚀

GRAM Qwen3 4B RewardModel Parameters and Internals

LLM NameGRAM Qwen3 4B RewardModel
Repository 🤗https://huggingface.co/NiuTrans/GRAM-Qwen3-4B-RewardModel 
Base Model(s)  Qwen/Qwen3-4B   Qwen/Qwen3-4B
Model Size4b
Required VRAM8.1 GB
Updated2025-07-02
MaintainerNiuTrans
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.1 GB: 2-of-2   0.0 GB
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.52.4
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to GRAM Qwen3 4B RewardModel

Best Alternatives
Context / RAM
Downloads
Likes
Jan Nano 128K128K / 8.1 GB2681175
Polaris 4B Preview128K / 8.1 GB1785105
Jan Nano 128K128K / 8.1 GB1342
Jan Nano40K / 8.1 GB34247432
Qwen3 Embedding 4B40K / 8.1 GB7795785
Qwen3 Reranker 4B40K / 8.1 GB3520771
QVikhr 3 4B Instruction40K / 8.1 GB1489
Qwen3 4B FP840K / 5.2 GB1466723
Qwen3 4B40K / 8.1 GB173198
Jan Nano40K / 8.1 GB5435
Note: green Score (e.g. "73.2") means that the model is better than NiuTrans/GRAM-Qwen3-4B-RewardModel.

Rank the GRAM Qwen3 4B RewardModel 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? 49328 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