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

DeepSeek R1 0528 Quantized.w4a16 by RedHatAI

 »  All LLMs  »  RedHatAI  »  DeepSeek R1 0528 Quantized.w4a16   URL Share it on

  674   
Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Compressed-tensors   Conversational   Custom code   Deepseek   Deepseek v3   Gptq   Int4   Llmcompressor   Neuralmagic   Quantized   Redhat   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/RedHatAI/DeepSeek-R1-0528-quantized.w4a16 

DeepSeek R1 0528 Quantized.w4a16 Benchmarks

LLME Score: 0.32639
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

DeepSeek R1 0528 Quantized.w4a16 Parameters and Internals

LLM NameDeepSeek R1 0528 Quantized.w4a16
Repository 🤗https://huggingface.co/RedHatAI/DeepSeek-R1-0528-quantized.w4a16 
Base Model(s)  DeepSeek R1 0528   deepseek-ai/DeepSeek-R1-0528
Required VRAM263.8 GB
Updated2025-06-09
MaintainerRedHatAI
Model Typedeepseek_v3
Model Files  1.9 GB: 1-of-63   1.2 GB: 2-of-63   1.2 GB: 3-of-63   1.2 GB: 4-of-63   6.3 GB: 5-of-63   6.3 GB: 6-of-63   6.3 GB: 7-of-63   6.3 GB: 8-of-63   6.3 GB: 9-of-63   6.3 GB: 10-of-63   6.3 GB: 11-of-63   6.3 GB: 12-of-63   6.3 GB: 13-of-63   6.3 GB: 14-of-63   6.3 GB: 15-of-63   6.3 GB: 16-of-63   6.3 GB: 17-of-63   6.3 GB: 18-of-63   6.3 GB: 19-of-63   6.3 GB: 20-of-63   6.3 GB: 21-of-63   6.3 GB: 22-of-63   6.3 GB: 23-of-63   6.3 GB: 24-of-63   6.3 GB: 25-of-63   6.3 GB: 26-of-63   6.3 GB: 27-of-63   6.3 GB: 28-of-63   6.3 GB: 29-of-63   6.3 GB: 30-of-63   6.3 GB: 31-of-63   6.3 GB: 32-of-63   6.3 GB: 33-of-63   6.3 GB: 34-of-63   6.3 GB: 35-of-63   6.3 GB: 36-of-63   6.3 GB: 37-of-63   6.3 GB: 38-of-63   6.3 GB: 39-of-63   6.3 GB: 40-of-63   6.3 GB: 41-of-63   6.3 GB: 42-of-63   6.3 GB: 43-of-63   6.3 GB: 44-of-63   6.3 GB: 45-of-63
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureDeepseekV3ForCausalLM
Licensemit
Context Length163840
Model Max Length163840
Transformers Version4.52.0.dev0
Vocabulary Size129280
Torch Data Typebfloat16
DeepSeek R1 0528 Quantized.w4a16 (RedHatAI/DeepSeek-R1-0528-quantized.w4a16)

Best Alternatives to DeepSeek R1 0528 Quantized.w4a16

Best Alternatives
Context / RAM
Downloads
Likes
DeepSeek R1 0528 GGUF160K /  GB81173138
DeepSeek V3 AWQ160K / 351.9 GB288834
DeepSeek R1 GGUF160K /  GB543471075
DeepSeek V3.0324 GGUF160K /  GB109917186
DeepSeek R1 0528 AWQ160K / 205 GB696212
DeepSeek R1 FP4160K / 226.6 GB45291253
DeepSeek R1 0528 FP4160K / 107 GB37217
DeepSeek V3.0324 GGUF UD160K /  GB86329
DeepSeek R1 GGUF UD160K /  GB421516
DeepSeek V3.0324 AWQ160K / 351.9 GB644320
Note: green Score (e.g. "73.2") means that the model is better than RedHatAI/DeepSeek-R1-0528-quantized.w4a16.

Rank the DeepSeek R1 0528 Quantized.w4a16 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? 48023 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