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

Cogito V2 Preview Deepseek 671B MoE by deepcogito

 »  All LLMs  »  deepcogito  »  Cogito V2 Preview Deepseek 671B MoE   URL Share it on

  39   
  Autotrain compatible Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Conversational   Custom code   Deepseek v3   Endpoints compatible   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/deepcogito/cogito-v2-preview-deepseek-671B-MoE 

Cogito V2 Preview Deepseek 671B MoE Benchmarks

LLME Score: 0.27514
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cogito V2 Preview Deepseek 671B MoE (deepcogito/cogito-v2-preview-deepseek-671B-MoE)
🌟 Advertise your project 🚀

Cogito V2 Preview Deepseek 671B MoE Parameters and Internals

LLM NameCogito V2 Preview Deepseek 671B MoE
Repository 🤗https://huggingface.co/deepcogito/cogito-v2-preview-deepseek-671B-MoE 
Base Model(s)  DeepSeek V3 Base   deepseek-ai/DeepSeek-V3-Base
Model Size671b
Required VRAM219.9 GB
Updated2025-09-15
Maintainerdeepcogito
Model Typedeepseek_v3
Model Files  4.9 GB: 1-of-270   5.0 GB: 2-of-270   5.0 GB: 3-of-270   5.0 GB: 4-of-270   5.0 GB: 5-of-270   5.0 GB: 6-of-270   5.0 GB: 7-of-270   5.0 GB: 8-of-270   5.0 GB: 9-of-270   5.0 GB: 10-of-270   5.0 GB: 11-of-270   5.0 GB: 12-of-270   5.0 GB: 13-of-270   5.0 GB: 14-of-270   5.0 GB: 15-of-270   5.0 GB: 16-of-270   5.0 GB: 17-of-270   5.0 GB: 18-of-270   5.0 GB: 19-of-270   5.0 GB: 20-of-270   5.0 GB: 21-of-270   5.0 GB: 22-of-270   5.0 GB: 23-of-270   5.0 GB: 24-of-270   5.0 GB: 25-of-270   5.0 GB: 26-of-270   5.0 GB: 27-of-270   5.0 GB: 28-of-270   5.0 GB: 29-of-270   5.0 GB: 30-of-270   5.0 GB: 31-of-270   5.0 GB: 32-of-270   5.0 GB: 33-of-270   5.0 GB: 34-of-270   5.0 GB: 35-of-270   5.0 GB: 36-of-270   5.0 GB: 37-of-270   5.0 GB: 38-of-270   5.0 GB: 39-of-270   5.0 GB: 40-of-270   5.0 GB: 41-of-270   5.0 GB: 42-of-270   5.0 GB: 43-of-270   5.0 GB: 44-of-270
Model ArchitectureDeepseekV3ForCausalLM
Licensemit
Context Length163840
Model Max Length163840
Transformers Version4.53.0
Vocabulary Size128815
Torch Data Typebfloat16

Best Alternatives to Cogito V2 Preview Deepseek 671B MoE

Best Alternatives
Context / RAM
Downloads
Likes
R1 1776160K / 243.4 GB243992310
DeepSeek Prover V2 671B160K / 189 GB1448810
Deepseek V3.1 MLX 5.5bit160K / 231 GB27725
MAI DS R1160K / 1346.5 GB1248286
DeepSeek Prover V2 671B160K / 184.7 GB173
DeepSeek V3.1 4bit160K / 190.1 GB31616
DeepSeek V3.1 8bit160K / 177.8 GB25683
DeepSeek V3.1 Base 4bit160K / 190.1 GB28673
DeepSeek R1 0528 5bit160K / 231 GB1253
DeepSeek Prover V2 671B GGUF160K / 250 GB15818
Note: green Score (e.g. "73.2") means that the model is better than deepcogito/cogito-v2-preview-deepseek-671B-MoE.

Rank the Cogito V2 Preview Deepseek 671B MoE 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? 51369 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