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

DeepSeek V4 Pro by deepseek-ai

 »  All LLMs  »  deepseek-ai  »  DeepSeek V4 Pro   URL Share it on

  30   

DeepSeek V4 Pro is an open-source language model by deepseek-ai. Features: 861.6b LLM, VRAM: 557.9GB, Context: 1024K, License: mit, LLM Explorer Score: 0.52.

  8-bit   Conversational   Deepseek v4   Endpoints compatible   Eval-results   Fp8   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro 

DeepSeek V4 Pro Benchmarks

LLME Score: 0.52225
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepSeek V4 Pro (deepseek-ai/DeepSeek-V4-Pro)
🌟 Advertise your project 🚀

DeepSeek V4 Pro Parameters and Internals

LLM NameDeepSeek V4 Pro
Repository 🤗https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro 
Model Size861.6b
Required VRAM557.9 GB
Updated2026-04-24
Maintainerdeepseek-ai
Model Typedeepseek_v4
Model Files  1.9 GB: 1-of-64   13.9 GB: 2-of-64   13.9 GB: 3-of-64   13.9 GB: 4-of-64   13.9 GB: 5-of-64   13.9 GB: 6-of-64   13.9 GB: 7-of-64   13.9 GB: 8-of-64   13.9 GB: 9-of-64   13.9 GB: 10-of-64   13.9 GB: 11-of-64   13.9 GB: 12-of-64   13.9 GB: 13-of-64   13.9 GB: 14-of-64   13.9 GB: 15-of-64   13.9 GB: 16-of-64   13.9 GB: 17-of-64   13.9 GB: 18-of-64   13.9 GB: 19-of-64   13.9 GB: 20-of-64   13.9 GB: 21-of-64   13.9 GB: 22-of-64   13.9 GB: 23-of-64   13.9 GB: 24-of-64   13.9 GB: 25-of-64   13.9 GB: 26-of-64   13.9 GB: 27-of-64   13.9 GB: 28-of-64   13.9 GB: 29-of-64   13.9 GB: 30-of-64   13.9 GB: 31-of-64   13.9 GB: 32-of-64   13.9 GB: 33-of-64   13.9 GB: 34-of-64   13.9 GB: 35-of-64   13.9 GB: 36-of-64   13.9 GB: 37-of-64   13.9 GB: 38-of-64   13.9 GB: 39-of-64   13.9 GB: 40-of-64   13.9 GB: 41-of-64
Model ArchitectureDeepseekV4ForCausalLM
Licensemit
Context Length1048576
Model Max Length1048576
Transformers Version4.57.1
Vocabulary Size129280
Torch Data Typebfloat16

Rank the DeepSeek V4 Pro 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? 53185 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer