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 Llm 67B Base AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Deepseek Llm 67B Base AWQ   URL Share it on

  32   

Deepseek Llm 67B Base AWQ is an open-source language model by TheBloke. Features: 67b LLM, VRAM: 37.5GB, Context: 4K, License: other, Quantized, LLM Explorer Score: 0.1.

  4-bit   Awq Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/deepseek-llm-67b-base-AWQ 

Deepseek Llm 67B Base AWQ Benchmarks

LLME Score: 0.10273
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Deepseek Llm 67B Base AWQ (TheBloke/deepseek-llm-67b-base-AWQ)
🌟 Advertise your project 🚀

Deepseek Llm 67B Base AWQ Parameters and Internals

Model Type 
yi
Additional Notes 
DeepSeek LLM supports commercial use.
Supported Languages 
english (high), chinese (high)
Training Details 
Data Volume:
2 trillion tokens
Model Architecture:
Grouped-Query Attention
Input Output 
Input Format:
{prompt}
LLM NameDeepseek Llm 67B Base AWQ
Repository 🤗https://huggingface.co/TheBloke/deepseek-llm-67b-base-AWQ 
Model NameDeepseek LLM 67B Base
Model CreatorDeepSeek
Base Model(s)  Deepseek Llm 67B Base   deepseek-ai/deepseek-llm-67b-base
Model Size67b
Required VRAM37.5 GB
Updated2026-06-06
MaintainerTheBloke
Model Typellama
Model Files  10.0 GB: 1-of-4   9.9 GB: 2-of-4   10.0 GB: 3-of-4   7.6 GB: 4-of-4
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>
Vocabulary Size102400
Torch Data Typefloat16

Best Alternatives to Deepseek Llm 67B Base AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...uddy Deepseek 67B V15 Base AWQ4K / 37.5 GB80
Deepseek Llm 67B Chat AWQ4K / 37.5 GB305
...67B Spicy 3.1 1 5.0bpw H6 EXL24K / 43.7 GB41
...ek Llm 67B Chat 2.4bpw H6 EXL24K / 22.2 GB72
...k Llm 67B Chat 2.65bpw H6 EXL24K / 24.2 GB41
...ek Llm 67B Chat 3.0bpw H6 EXL24K / 27.1 GB41
Deepseek Llm 67B Chat4K / 135 GB2295206
Deepseek Llm 67B Base4K / 135 GB20663128
...penbuddy Deepseek 67B V18.1 4K4K / 135 GB81821
Openbuddy Deepseek 67B V15.24K / 135 GB190510
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/deepseek-llm-67b-base-AWQ.

Rank the Deepseek Llm 67B Base 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? 54415 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