Gemma 2 27B It GGUF by gaianet

 ยป  All LLMs  ยป  gaianet  ยป  Gemma 2 27B It GGUF   URL Share it on

  Autotrain compatible Base model:google/gemma-2-27b-... Base model:quantized:google/ge...   Conversational   Fp16   Gemma2   Gguf   Q2   Quantized   Region:us

Gemma 2 27B It GGUF Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 2 27B It GGUF (gaianet/gemma-2-27b-it-GGUF)

Gemma 2 27B It GGUF Parameters and Internals

Model Type 
text generation
Additional Notes 
Quantized with llama.cpp b3259.
Input Output 
Input Format:
gemma-instruct
LLM NameGemma 2 27B It GGUF
Repository ๐Ÿค—https://huggingface.co/gaianet/gemma-2-27b-it-GGUF 
Model Namegemma-2-27b-it
Model CreatorGoogle
Base Model(s)  Gemma 2 27B It   google/gemma-2-27b-it
Model Size27b
Required VRAM10.4 GB
Updated2025-01-16
Maintainergaianet
Model Typegemma2
Model Files  10.4 GB   14.5 GB   13.4 GB   12.2 GB   15.6 GB   16.6 GB   15.7 GB   18.9 GB   19.4 GB   18.9 GB   22.3 GB   28.9 GB   29.9 GB: 1-of-2   24.6 GB: 2-of-2
GGUF QuantizationYes
Quantization Typefp16|gguf|q2|q4_k|q5_k
Model ArchitectureGemma2ForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.42.0.dev0
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Gemma 2 27B It GGUF

Best Alternatives
Context / RAM
Downloads
Likes
...Horizon AI Korean Advanced 27B8K / 54.7 GB14580
Gemma 2 27B It GGUF8K / 10.4 GB1367
Gemma 2 27B It 4bit8K / 15.3 GB2513778
Gemma2 Mixed Therapy Ft8K / 15.8 GB781
Gemma 2 27B It Bnb 4bit8K / 15.8 GB404811
Gemma 2 27B Bnb 4bit8K / 15.8 GB294212
GEMMA2 27B NLI 16bit8K / 54.7 GB120
Gemma 2 27B It 8bit8K / 28.8 GB8810
Gemma 2 27B It 4bit8K / 15.8 GB393
Gemma 2 27B 4bit8K / 15.3 GB420
Note: green Score (e.g. "73.2") means that the model is better than gaianet/gemma-2-27b-it-GGUF.

Rank the Gemma 2 27B It GGUF Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 41470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227