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 R1 0528 AWQ by cognitivecomputations

 »  All LLMs  »  cognitivecomputations  »  DeepSeek R1 0528 AWQ   URL Share it on

  1240   

DeepSeek R1 0528 AWQ is an open-source language model by cognitivecomputations. Features: 671b LLM, VRAM: 205GB, Context: 160K, License: mit, Quantized, LLM Explorer Score: 0.22.

  4-bit   Awq Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Conversational   Custom code   Deepseek v3   En   Endpoints compatible   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/QuixiAI/DeepSeek-R1-0528-AWQ 

DeepSeek R1 0528 AWQ Benchmarks

LLME Score: 0.21727
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepSeek R1 0528 AWQ (QuixiAI/DeepSeek-R1-0528-AWQ)
🌟 Advertise your project 🚀

DeepSeek R1 0528 AWQ Parameters and Internals

LLM NameDeepSeek R1 0528 AWQ
Repository 🤗https://huggingface.co/QuixiAI/DeepSeek-R1-0528-AWQ 
Base Model(s)  DeepSeek R1 0528   deepseek-ai/DeepSeek-R1-0528
Model Size671b
Required VRAM205 GB
Updated2026-05-17
Maintainercognitivecomputations
Model Typedeepseek_v3
Model Files  5.0 GB: 1-of-74   5.0 GB: 2-of-74   5.0 GB: 3-of-74   5.0 GB: 4-of-74   5.0 GB: 5-of-74   5.0 GB: 6-of-74   5.0 GB: 7-of-74   5.0 GB: 8-of-74   5.0 GB: 9-of-74   5.0 GB: 10-of-74   5.0 GB: 11-of-74   5.0 GB: 12-of-74   5.0 GB: 13-of-74   5.0 GB: 14-of-74   5.0 GB: 15-of-74   5.0 GB: 16-of-74   5.0 GB: 17-of-74   5.0 GB: 18-of-74   5.0 GB: 19-of-74   5.0 GB: 20-of-74   5.0 GB: 21-of-74   5.0 GB: 22-of-74   5.0 GB: 23-of-74   5.0 GB: 24-of-74   5.0 GB: 25-of-74   5.0 GB: 26-of-74   5.0 GB: 27-of-74   5.0 GB: 28-of-74   5.0 GB: 29-of-74   5.0 GB: 30-of-74   5.0 GB: 31-of-74   5.0 GB: 32-of-74   5.0 GB: 33-of-74   5.0 GB: 34-of-74   5.0 GB: 35-of-74   5.0 GB: 36-of-74   5.0 GB: 37-of-74   5.0 GB: 38-of-74   5.0 GB: 39-of-74   5.0 GB: 40-of-74   5.0 GB: 41-of-74
Supported Languagesen zh
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureDeepseekV3ForCausalLM
Licensemit
Context Length163840
Model Max Length163840
Transformers Version4.52.4
Vocabulary Size129280
Torch Data Typebfloat16

Best Alternatives to DeepSeek R1 0528 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
DeepSeek V3 AWQ160K / 351.9 GB28035
DeepSeek R1 AWQ160K / 225 GB89686
DeepSeek V3.0324 AWQ160K / 351.9 GB31723
RakutenAI 3.0 MLX 4bit160K / 198.7 GB1092
DeepSeek V3.1 8bit160K / 177.8 GB27313
DeepSeek V3.1 Terminus 4bit160K / 190.1 GB1432
DeepSeek V3.1 Base 4bit160K / 190.1 GB1563
DeepSeek R1 0528 5bit160K / 231 GB1023
R1 1776160K / 243.4 GB8552324
DeepSeek Prover V2 671B160K / 189 GB704829
Note: green Score (e.g. "73.2") means that the model is better than QuixiAI/DeepSeek-R1-0528-AWQ.

Rank the DeepSeek R1 0528 AWQ 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? 53834 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