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

DeepSeek R1 FP4 V2 by nvidia

 »  All LLMs  »  nvidia  »  DeepSeek R1 FP4 V2   URL Share it on

  108   
  8-bit Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Conversational   Custom code   Deepseek v3   Deepseekr1   Fp4   Model optimizer   Modelopt   Nvidia   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/DeepSeek-R1-FP4-v2 

DeepSeek R1 FP4 V2 Benchmarks

LLME Score: 0.25976
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepSeek R1 FP4 V2 (nvidia/DeepSeek-R1-FP4-v2)
🌟 Advertise your project 🚀

DeepSeek R1 FP4 V2 Parameters and Internals

LLM NameDeepSeek R1 FP4 V2
Repository 🤗https://huggingface.co/nvidia/DeepSeek-R1-FP4-v2 
Base Model(s)  DeepSeek R1   deepseek-ai/DeepSeek-R1
Model Size393.6b
Required VRAM103.5 GB
Updated2025-09-06
Maintainernvidia
Model Typedeepseek_v3
Model Files  4.2 GB: 1-of-163   2.4 GB: 2-of-163   2.4 GB: 3-of-163   2.5 GB: 4-of-163   2.4 GB: 5-of-163   2.6 GB: 6-of-163   2.4 GB: 7-of-163   2.4 GB: 8-of-163   2.5 GB: 9-of-163   2.4 GB: 10-of-163   2.4 GB: 11-of-163   0.7 GB: 12-of-163   2.5 GB: 13-of-163   2.4 GB: 14-of-163   2.5 GB: 15-of-163   2.4 GB: 16-of-163   2.4 GB: 17-of-163   2.5 GB: 18-of-163   2.4 GB: 19-of-163   2.4 GB: 20-of-163   2.5 GB: 21-of-163   2.4 GB: 22-of-163   2.5 GB: 23-of-163   2.4 GB: 24-of-163   2.4 GB: 25-of-163   2.5 GB: 26-of-163   2.4 GB: 27-of-163   2.4 GB: 28-of-163   2.5 GB: 29-of-163   2.4 GB: 30-of-163   2.5 GB: 31-of-163   2.4 GB: 32-of-163   2.4 GB: 33-of-163   1.0 GB: 34-of-163   2.5 GB: 35-of-163   2.4 GB: 36-of-163   2.5 GB: 37-of-163   2.4 GB: 38-of-163   2.4 GB: 39-of-163   2.5 GB: 40-of-163   2.4 GB: 41-of-163   2.4 GB: 42-of-163   2.5 GB: 43-of-163
Model ArchitectureDeepseekV3ForCausalLM
Licensemit
Context Length163840
Model Max Length163840
Transformers Version4.46.3
Vocabulary Size129280
Torch Data Typebfloat16

Best Alternatives to DeepSeek R1 FP4 V2

Best Alternatives
Context / RAM
Downloads
Likes
DeepSeek R1 0528 FP4 V2160K / 103.5 GB133073
Note: green Score (e.g. "73.2") means that the model is better than nvidia/DeepSeek-R1-FP4-v2.

Rank the DeepSeek R1 FP4 V2 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? 51148 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