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

Griffin 3B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Griffin 3B GPTQ   URL Share it on

  9   
  4-bit   Autotrain compatible   Base model:acrastt/griffin-3b Base model:quantized:acrastt/g...   Dataset:ldjnr/puffin   En   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Griffin-3B-GPTQ 

Griffin 3B GPTQ Benchmarks

LLME Score: 0.10627
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Griffin 3B GPTQ (TheBloke/Griffin-3B-GPTQ)
🌟 Advertise your project 🚀

Griffin 3B GPTQ Parameters and Internals

Model Type 
llama, text generation
Additional Notes 
Based on OpenLLaMA 3B V2 and finetuned on the Puffin dataset for 1 epoch. Multiple GPTQ parameter permutations are available for different performance criteria. Quantized by TheBloke with several parameter options for GPU and CPU+GPU inference.
Training Details 
Data Sources:
https://huggingface.co/datasets/LDJnr/Puffin
Methodology:
Finetuning for 1 epoch
Input Output 
Input Format:
### HUMAN: {prompt} ### RESPONSE:
LLM NameGriffin 3B GPTQ
Repository 🤗https://huggingface.co/TheBloke/Griffin-3B-GPTQ 
Model NameGriffin 3B
Model CreatorBohan Du
Base Model(s)  Griffin 3B   acrastt/Griffin-3B
Model Size3b
Required VRAM2.1 GB
Updated2025-08-22
MaintainerTheBloke
Model Typellama
Model Files  2.1 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.30.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Griffin 3B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...ma 3.2 3B Instruct XMADai INT4128K / 3 GB346
Open Llama 3b V2 8K GPTQ8K / 2 GB133
Orca2myth7.2 GPTQ4K / 10.9 GB64
...B GPTQ 4bit GPTQ Code Instruct2K / 2 GB50
...lInstruct Lora Merged 4bit 32g2K / 2.3 GB132
...zard Evol Instuct V2 196K GPTQ2K / 2.1 GB322
...ama 3B Mathwizard Quantized V22K / 3.7 GB60
SauerkrautLM 3B V1 GPTQ2K / 2.3 GB92
Marx 3B GPTQ2K / 2.1 GB73
Puma 3B GPTQ2K / 2.1 GB101
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Griffin-3B-GPTQ.

Rank the Griffin 3B GPTQ 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? 50835 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