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 GGML by TheBloke

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

  2   
  Base model:acrastt/griffin-3b Base model:finetune:acrastt/gr...   Dataset:ldjnr/puffin   En   Ggml   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/Griffin-3B-GGML 

Griffin 3B GGML Benchmarks

LLME Score: 0.1064
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Griffin 3B GGML (TheBloke/Griffin-3B-GGML)
🌟 Advertise your project 🚀

Griffin 3B GGML Parameters and Internals

Model Type 
text-generation, GGML
Use Cases 
Limitations:
Not expected to be very good since it was a starting finetuning effort
Additional Notes 
The model GGML files are compatible with llama.cpp and other supporting libraries/UI for both CPU and GPU inference.
Training Details 
Data Sources:
Puffin dataset
Methodology:
Finetuned from OpenLLaMA 3B V2
Training Time:
1 epoch
Model Architecture:
OpenLLaMA
Input Output 
Input Format:
### HUMAN: {prompt} ### RESPONSE:
Output Format:
Text
LLM NameGriffin 3B GGML
Repository 🤗https://huggingface.co/TheBloke/Griffin-3B-GGML 
Model NameGriffin 3B
Model CreatorBohan Du
Base Model(s)  Griffin 3B   acrastt/Griffin-3B
Model Size3b
Required VRAM1.9 GB
Updated2025-08-23
MaintainerTheBloke
Model Typellama
Model Files  1.9 GB   2.1 GB   2.4 GB   2.6 GB   3.6 GB
Supported Languagesen
GGML QuantizationYes
Quantization Typeggml
Model ArchitectureAutoModel
Licenseapache-2.0

Best Alternatives to Griffin 3B GGML

Best Alternatives
Context / RAM
Downloads
Likes
Marx 3B GGML0K / 1.9 GB57
Puma 3B GGML0K / 1.9 GB23
...blecode Instruct Alpha 3B GGML0K / 1.6 GB443
...de Completion Alpha 3B 4K GGML0K / 1.6 GB323
Open Llama GGML0K / 1.9 GB49
Bloomz GGML0K / 0.5 GB86
Stablelm GGML0K / 2 GB33
Bloom GGML0K / 0.5 GB148
Redpajama 3B GGML0K / 1.6 GB48
Diraya 3B Instruct Ar0K / 0 GB53
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Griffin-3B-GGML.

Rank the Griffin 3B GGML 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