gemma-2-27b-ov

gemma-2-27b-ov is an OpenVino int4 quantized version of Google's Gemma-2 27B model with Instruct Training (IT), providing a very fast inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU (works best with 64 GB of memory).

gemma-2-27b-ov is a leading open source foundation model from Google.

Model Description

• Developed by: Google
• Quantized by: llmware
• Model type: gemma-2b
• Parameters: 2 billion
• Model Parent: google/gemma-2-27b-it
• Language(s) (NLP): English
• License: Apache 2.0
• Uses: General purpose chat
• RAG Benchmark Accuracy Score: NA
• Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website