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 Flash by deepseek-ai

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

  3088308   

DeepSeek V4 Flash is an open-source language model by deepseek-ai. Features: 158.1b LLM, VRAM: 145.1GB, Context: 1024K, License: mit, LLM Explorer Score: 0.7, ELO: 1434.

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

DeepSeek V4 Flash Benchmarks

LMSys ELO: 1434 vs 1272 (so35)12.7%
LLME Score: 0.70357
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepSeek V4 Flash (deepseek-ai/DeepSeek-V4-Flash)
🌟 Advertise your project 🚀

DeepSeek V4 Flash Parameters and Internals

LLM NameDeepSeek V4 Flash
Repository 🤗https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash 
Model Size158.1b
Required VRAM145.1 GB
Updated2026-05-28
Maintainerdeepseek-ai
Model Typedeepseek_v4
Model Files  1.1 GB: 1-of-46   3.6 GB: 2-of-46   3.6 GB: 3-of-46   3.6 GB: 4-of-46   3.6 GB: 5-of-46   3.6 GB: 6-of-46   3.6 GB: 7-of-46   3.6 GB: 8-of-46   3.6 GB: 9-of-46   3.6 GB: 10-of-46   3.6 GB: 11-of-46   3.6 GB: 12-of-46   3.6 GB: 13-of-46   3.6 GB: 14-of-46   3.6 GB: 15-of-46   3.6 GB: 16-of-46   3.6 GB: 17-of-46   3.6 GB: 18-of-46   3.6 GB: 19-of-46   3.6 GB: 20-of-46   3.6 GB: 21-of-46   3.6 GB: 22-of-46   3.6 GB: 23-of-46   3.6 GB: 24-of-46   3.6 GB: 25-of-46   3.6 GB: 26-of-46   3.6 GB: 27-of-46   3.6 GB: 28-of-46   3.6 GB: 29-of-46   3.6 GB: 30-of-46   3.6 GB: 31-of-46   3.6 GB: 32-of-46   3.6 GB: 33-of-46   3.6 GB: 34-of-46   3.6 GB: 35-of-46   3.6 GB: 36-of-46   3.6 GB: 37-of-46   3.6 GB: 38-of-46   3.6 GB: 39-of-46   3.6 GB: 40-of-46   3.6 GB: 41-of-46
Model ArchitectureDeepseekV4ForCausalLM
Licensemit
Context Length1048576
Model Max Length1048576
Transformers Version4.57.1
Vocabulary Size129280
Torch Data Typebfloat16

Quantized Models of the DeepSeek V4 Flash

Model
Likes
Downloads
VRAM
...seek Ai DeepSeek V4 Flash 8bit124922215 GB
...seek Ai DeepSeek V4 Flash 4bit44178159 GB

Best Alternatives to DeepSeek V4 Flash

Best Alternatives
Context / RAM
Downloads
Likes
DeepSeek V4 Flash1024K / 145.1 GB203665

Rank the DeepSeek V4 Flash 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? 54415 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