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

ZR1 1.5B by Zyphra

 »  All LLMs  »  Zyphra  »  ZR1 1.5B   URL Share it on

  1269   
  Arxiv:2502.01456   Arxiv:2503.07572   Autotrain compatible Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Conversational   Dataset:ai-mo/numinamath-cot   Dataset:baai/taco   Dataset:codeparrot/apps   Dataset:deepmind/code contests Dataset:matrixstudio/codeforce...   En   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Zyphra/ZR1-1.5B 

ZR1 1.5B Benchmarks

LLME Score: 0.38027
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ZR1 1.5B (Zyphra/ZR1-1.5B)

ZR1 1.5B Parameters and Internals

LLM NameZR1 1.5B
Repository 🤗https://huggingface.co/Zyphra/ZR1-1.5B 
Base Model(s)  deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B   deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Model Size1.5b
Required VRAM7.1 GB
Updated2025-04-23
MaintainerZyphra
Model Typeqwen2
Model Files  5.0 GB: 1-of-2   2.1 GB: 2-of-2
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.50.3
Tokenizer ClassLlamaTokenizerFast
Padding Token<｜end▁of▁sentence｜>
Vocabulary Size151936
Torch Data Typebfloat16

Best Alternatives to ZR1 1.5B

Best Alternatives
Context / RAM
Downloads
Likes
ReaderLM V2500K / 3.1 GB71731609
Reader Lm 1.5B250K / 3.1 GB597596
DeepSeek R1 Distill Qwen 1.5B128K / 3.5 GB16993831168
DeepScaleR 1.5B Preview128K / 7.1 GB62611548
DeepCoder 1.5B Preview128K / 7.1 GB235362
Qwen2.5 1.5B128K / 3.1 GB78103398
Open RS3128K / 0 GB584119
AlphaMaze V0.2 1.5B128K / 3.5 GB260992
Qwen2 1.5B128K / 3.1 GB16395991
Stella En 1.5B V5128K / 6.2 GB581890211
Note: green Score (e.g. "73.2") means that the model is better than Zyphra/ZR1-1.5B.

Rank the ZR1 1.5B 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? 46599 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