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

GEITje 7B Chat AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  GEITje 7B Chat AWQ   URL Share it on

  11   
  4-bit   Autotrain compatible   Awq Base model:quantized:rijgersbe... Base model:rijgersberg/geitje-...   Conversational Dataset:rijgersberg/no robots ... Dataset:rijgersberg/ultrachat ...   Geitje   Generated from trainer   Mistral   Nl   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/GEITje-7B-chat-AWQ 

GEITje 7B Chat AWQ Benchmarks

LLME Score: 0.13906
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
GEITje 7B Chat AWQ (TheBloke/GEITje-7B-chat-AWQ)

GEITje 7B Chat AWQ Parameters and Internals

Model Type 
conversational
Use Cases 
Areas:
Language modeling, Conversational AI
Applications:
Chat applications
Primary Use Cases:
Following instructions, Answering questions, Holding dialogues
Additional Notes 
GEITje has been fine-tuned specifically for Dutch text.
Supported Languages 
nl (high)
Training Details 
Data Sources:
Dutch Gigacorpus, MADLAD-400
Data Volume:
10 billion tokens
Methodology:
full-parameter finetune
Context Length:
8192
Model Architecture:
Mistral 7B architecture
Input Output 
Input Format:
<|user|> {prompt} <|assistant|>
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Use the AWQ method for optimized performance.
LLM NameGEITje 7B Chat AWQ
Repository 🤗https://huggingface.co/TheBloke/GEITje-7B-chat-AWQ 
Model NameGeitje 7B Chat
Model CreatorEdwin Rijgersberg
Base Model(s)  GEITje 7B Chat   Rijgersberg/GEITje-7B-chat
Model Size7b
Required VRAM4.2 GB
Updated2025-06-01
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
Supported Languagesnl
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to GEITje 7B Chat AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB130
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB342324
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB13779144
Ghost 7B Alpha AWQ32K / 4.2 GB230
Breeze 7B Instruct V1.0 AWQ32K / 4.6 GB560
...Instruct V0.2 AWQ 4bit Smashed32K / 4.2 GB2291
Tess 7B V2.0 AWQ32K / 4.2 GB211
...reeze 7B 32K Instruct V1.0 AWQ32K / 4.7 GB90
Mahou 1.3a Mistral 7B AWQ32K / 4.2 GB101
Mahou 1.3 Mistral 7B AWQ32K / 4.2 GB130
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/GEITje-7B-chat-AWQ.

Rank the GEITje 7B Chat 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? 47753 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 v20241227
  Support LLM Explorer