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

DeepSeek V3.1 AWQ by QuantTrio

 »  All LLMs  »  QuantTrio  »  DeepSeek V3.1 AWQ   URL Share it on

  116   
  Arxiv:2412.19437   4-bit   Autotrain compatible   Awq Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Conversational   Custom code   Deepseek v3   En   Endpoints compatible   Gptq   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Vllm   Zh
Model Card on HF 🤗: https://huggingface.co/QuantTrio/DeepSeek-V3.1-AWQ 

DeepSeek V3.1 AWQ Benchmarks

LLME Score: 0.33218
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepSeek V3.1 AWQ (QuantTrio/DeepSeek-V3.1-AWQ)
🌟 Advertise your project 🚀

DeepSeek V3.1 AWQ Parameters and Internals

LLM NameDeepSeek V3.1 AWQ
Repository 🤗https://huggingface.co/QuantTrio/DeepSeek-V3.1-AWQ 
Base Model(s)  deepseek-ai/DeepSeek-V3.1   deepseek-ai/DeepSeek-V3.1
Required VRAM122.9 GB
Updated2025-08-26
MaintainerQuantTrio
Model Typedeepseek_v3
Model Files  2.9 GB: 1-of-134   3.0 GB: 2-of-134   3.0 GB: 3-of-134   3.0 GB: 4-of-134   3.0 GB: 5-of-134   3.0 GB: 6-of-134   3.0 GB: 7-of-134   3.0 GB: 8-of-134   3.0 GB: 9-of-134   3.0 GB: 10-of-134   3.0 GB: 11-of-134   3.0 GB: 12-of-134   3.0 GB: 13-of-134   3.0 GB: 14-of-134   3.0 GB: 15-of-134   3.0 GB: 16-of-134   3.0 GB: 17-of-134   3.0 GB: 18-of-134   3.0 GB: 19-of-134   3.0 GB: 20-of-134   3.0 GB: 21-of-134   3.0 GB: 22-of-134   3.0 GB: 23-of-134   3.0 GB: 24-of-134   3.0 GB: 25-of-134   3.0 GB: 26-of-134   3.0 GB: 27-of-134   3.0 GB: 28-of-134   3.0 GB: 29-of-134   3.0 GB: 30-of-134   3.0 GB: 31-of-134   3.0 GB: 32-of-134   3.0 GB: 33-of-134   3.0 GB: 34-of-134   3.0 GB: 35-of-134   3.0 GB: 36-of-134   3.0 GB: 37-of-134   3.0 GB: 38-of-134   3.0 GB: 39-of-134   3.0 GB: 40-of-134   3.0 GB: 41-of-134
Supported Languageszh en
GPTQ QuantizationYes
AWQ QuantizationYes
Quantization Typegptq|awq
Model ArchitectureDeepseekV3ForCausalLM
Licensemit
Context Length163840
Model Max Length163840
Transformers Version4.44.2
Vocabulary Size129280
Torch Data Typebfloat16

Best Alternatives to DeepSeek V3.1 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
DeepSeek V3 AWQ160K / 351.9 GB124835
DeepSeek V3 AWQ160K / 351.9 GB180934
DeepSeek R1 0528 AWQ160K / 205 GB849615
DeepSeek V3.1 AWQ W4AFP8160K / 225 GB352
DeepSeek R1 0528 AWQ160K / 205 GB196317
...epSeek R1 0528 Quantized.w4a16160K / 263.8 GB16019
DeepSeek V3.0324 AWQ160K / 351.9 GB406122
DeepSeek R1 AWQ160K / 225 GB398083
DeepSeek V3.0324 AWQ160K / 351.9 GB206823
DeepSeek R1 AWQ160K / 365 GB185085
Note: green Score (e.g. "73.2") means that the model is better than QuantTrio/DeepSeek-V3.1-AWQ.

Rank the DeepSeek V3.1 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? 50924 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