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 W4A16 AutoRound by Intel

 »  All LLMs  »  Intel  »  DeepSeek V4 Flash W4A16 AutoRound   URL Share it on

  84   

DeepSeek V4 Flash W4A16 AutoRound is an open-source language model by Intel. Features: 39.9b LLM, VRAM: 137.1GB, Context: 1024K, License: mit, LLM Explorer Score: 0.35.

  Arxiv:2309.05516   4-bit   Auto-round Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Deepseek v4   Endpoints compatible   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Intel/DeepSeek-V4-Flash-W4A16-AutoRound 

DeepSeek V4 Flash W4A16 AutoRound Benchmarks

LLME Score: 0.35308
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 W4A16 AutoRound (Intel/DeepSeek-V4-Flash-W4A16-AutoRound)
🌟 Advertise your project 🚀

DeepSeek V4 Flash W4A16 AutoRound Parameters and Internals

LLM NameDeepSeek V4 Flash W4A16 AutoRound
Repository 🤗https://huggingface.co/Intel/DeepSeek-V4-Flash-W4A16-AutoRound 
Base Model(s)  DeepSeek V4 Flash   deepseek-ai/DeepSeek-V4-Flash
Model Size39.9b
Required VRAM137.1 GB
Updated2026-04-28
MaintainerIntel
Model Typedeepseek_v4
Model Files  1.1 GB: 1-of-46   3.4 GB: 2-of-46   3.4 GB: 3-of-46   3.4 GB: 4-of-46   3.4 GB: 5-of-46   3.4 GB: 6-of-46   3.4 GB: 7-of-46   3.4 GB: 8-of-46   3.4 GB: 9-of-46   3.4 GB: 10-of-46   3.4 GB: 11-of-46   3.4 GB: 12-of-46   3.4 GB: 13-of-46   3.4 GB: 14-of-46   3.4 GB: 15-of-46   3.4 GB: 16-of-46   3.4 GB: 17-of-46   3.4 GB: 18-of-46   3.4 GB: 19-of-46   3.4 GB: 20-of-46   3.4 GB: 21-of-46   3.4 GB: 22-of-46   3.4 GB: 23-of-46   3.4 GB: 24-of-46   3.4 GB: 25-of-46   3.4 GB: 26-of-46   3.4 GB: 27-of-46   3.4 GB: 28-of-46   3.4 GB: 29-of-46   3.4 GB: 30-of-46   3.4 GB: 31-of-46   3.4 GB: 32-of-46   3.4 GB: 33-of-46   3.4 GB: 34-of-46   3.4 GB: 35-of-46   3.4 GB: 36-of-46   3.4 GB: 37-of-46   3.4 GB: 38-of-46   3.4 GB: 39-of-46   3.4 GB: 40-of-46   3.4 GB: 41-of-46
Model ArchitectureDeepseekV4ForCausalLM
Licensemit
Context Length1048576
Model Max Length1048576
Transformers Version4.57.1
Vocabulary Size129280
Torch Data Typebfloat16

Rank the DeepSeek V4 Flash W4A16 AutoRound 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? 53286 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