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 V2.5 by deepseek-ai

 »  All LLMs  »  deepseek-ai  »  DeepSeek V2.5   URL Share it on

  7517   

DeepSeek V2.5 is an open-source language model by deepseek-ai. Features: 235.7b LLM, VRAM: 378.4GB, Context: 160K, License: other, LLM Explorer Score: 0.36, ELO: 1307.

  Arxiv:2405.04434   Conversational   Custom code   Deepseek v2   Endpoints compatible   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/deepseek-ai/DeepSeek-V2.5 

DeepSeek V2.5 Benchmarks

LMSys ELO: 1307 vs 1272 (so35)2.8%
LLME Score: 0.35763
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepSeek V2.5 (deepseek-ai/DeepSeek-V2.5)
🌟 Advertise your project 🚀

DeepSeek V2.5 Parameters and Internals

Model Type 
general, coding
Additional Notes 
Supports function calling, JSON output, and FIM completion.
Input Output 
Input Format:
Chat-based template format using user-assistant roles.
Accepted Modalities:
text
Performance Tips:
Inference can be performed with Huggingface's Transformers or vLLM.
LLM NameDeepSeek V2.5
Repository 🤗https://huggingface.co/deepseek-ai/DeepSeek-V2.5 
Model Size235.7b
Required VRAM378.4 GB
Updated2026-05-15
Maintainerdeepseek-ai
Model Typedeepseek_v2
Model Files  8.6 GB: 1-of-55   8.6 GB: 2-of-55   8.6 GB: 3-of-55   8.6 GB: 4-of-55   8.6 GB: 5-of-55   8.6 GB: 6-of-55   8.6 GB: 7-of-55   8.6 GB: 8-of-55   8.6 GB: 9-of-55   8.6 GB: 10-of-55   8.6 GB: 11-of-55   8.6 GB: 12-of-55   8.6 GB: 13-of-55   8.6 GB: 14-of-55   8.6 GB: 15-of-55   8.6 GB: 16-of-55   8.6 GB: 17-of-55   8.6 GB: 18-of-55   8.6 GB: 19-of-55   8.6 GB: 20-of-55   8.6 GB: 21-of-55   8.6 GB: 22-of-55   8.6 GB: 23-of-55   8.6 GB: 24-of-55   8.6 GB: 25-of-55   8.6 GB: 26-of-55   8.6 GB: 27-of-55   8.6 GB: 28-of-55   8.6 GB: 29-of-55   8.6 GB: 30-of-55   8.6 GB: 31-of-55   8.6 GB: 32-of-55   8.6 GB: 33-of-55   8.6 GB: 34-of-55   8.6 GB: 35-of-55   8.6 GB: 36-of-55   8.6 GB: 37-of-55   8.6 GB: 38-of-55   8.6 GB: 39-of-55   8.6 GB: 40-of-55   8.6 GB: 41-of-55   8.6 GB: 42-of-55   8.6 GB: 43-of-55   8.6 GB: 44-of-55
Model ArchitectureDeepseekV2ForCausalLM
Licenseother
Context Length163840
Model Max Length163840
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>
Vocabulary Size102400
Torch Data Typebfloat16

Best Alternatives to DeepSeek V2.5

Best Alternatives
Context / RAM
Downloads
Likes
DeepSeek Coder V2 Instruct160K / 387 GB88248685
DeepSeek V2.5 1210160K / 378.4 GB873257
DeepSeek V2160K / 378.4 GB5335334
DeepSeek Coder V2 Base160K / 387 GB104281
DeepSeek V2 Chat160K / 378.4 GB9028462
DeepSeek V2 Chat 0628160K / 369.8 GB4360178
...eepSeek Coder V2 Instruct 0724160K / 378.4 GB326115
Note: green Score (e.g. "73.2") means that the model is better than deepseek-ai/DeepSeek-V2.5.

Rank the DeepSeek V2.5 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? 53999 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