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 Ai DeepSeek V4 Flash 8bit by mlx-community

 »  All LLMs  »  mlx-community  »  Deepseek Ai DeepSeek V4 Flash 8bit   URL Share it on

  5857   

Deepseek Ai DeepSeek V4 Flash 8bit is an open-source language model by mlx-community. Features: 284.3b LLM, VRAM: 215.2GB, Context: 1024K, License: mit, Quantized, LLM Explorer Score: 0.42.

  8-bit   8bit Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Deepseek v4   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/deepseek-ai-DeepSeek-V4-Flash-8bit 

Deepseek Ai DeepSeek V4 Flash 8bit Benchmarks

LLME Score: 0.41642
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Deepseek Ai DeepSeek V4 Flash 8bit (mlx-community/deepseek-ai-DeepSeek-V4-Flash-8bit)
🌟 Advertise your project 🚀

Deepseek Ai DeepSeek V4 Flash 8bit Parameters and Internals

LLM NameDeepseek Ai DeepSeek V4 Flash 8bit
Repository 🤗https://huggingface.co/mlx-community/deepseek-ai-DeepSeek-V4-Flash-8bit 
Base Model(s)  deepseek-ai/DeepSeek-V4-Flash   deepseek-ai/DeepSeek-V4-Flash
Model Size284.3b
Required VRAM215.2 GB
Updated2026-04-25
Maintainermlx-community
Model Typedeepseek_v4
Model Files  5.2 GB: 1-of-65   4.7 GB: 2-of-65   4.7 GB: 3-of-65   4.6 GB: 4-of-65   4.7 GB: 5-of-65   4.7 GB: 6-of-65   4.6 GB: 7-of-65   4.7 GB: 8-of-65   4.7 GB: 9-of-65   4.6 GB: 10-of-65   4.7 GB: 11-of-65   4.7 GB: 12-of-65   4.6 GB: 13-of-65   4.7 GB: 14-of-65   4.7 GB: 15-of-65   4.6 GB: 16-of-65   4.7 GB: 17-of-65   4.7 GB: 18-of-65   4.6 GB: 19-of-65   4.7 GB: 20-of-65   4.7 GB: 21-of-65   4.6 GB: 22-of-65   4.7 GB: 23-of-65   4.7 GB: 24-of-65   4.6 GB: 25-of-65   4.7 GB: 26-of-65   4.7 GB: 27-of-65   4.6 GB: 28-of-65   4.7 GB: 29-of-65   4.7 GB: 30-of-65   4.6 GB: 31-of-65   4.7 GB: 32-of-65   4.7 GB: 33-of-65   4.6 GB: 34-of-65   4.7 GB: 35-of-65   4.7 GB: 36-of-65   4.6 GB: 37-of-65   4.7 GB: 38-of-65   4.7 GB: 39-of-65   4.6 GB: 40-of-65   4.7 GB: 41-of-65   4.7 GB: 42-of-65   4.6 GB: 43-of-65   4.7 GB: 44-of-65   4.7 GB: 45-of-65   4.6 GB: 46-of-65
Quantization Type8bit
Model ArchitectureDeepseekV4ForCausalLM
Licensemit
Context Length1048576
Model Max Length1048576
Transformers Version4.57.1
Vocabulary Size129280
Torch Data Typebfloat16

Best Alternatives to Deepseek Ai DeepSeek V4 Flash 8bit

Best Alternatives
Context / RAM
Downloads
Likes
DeepSeek V4 Flash 4bit1024K / 152.2 GB44104

Rank the Deepseek Ai DeepSeek V4 Flash 8bit 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? 53205 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