mistral-nemo-instruct-2407-ov

mistral-nemo-instruct-2407-ov is an OpenVino int4 quantized version of mistral-nemo-instruct-2407-ov, providing a fast inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

mistral-nrmo-instruct-2407 is an innovative 12B Model from Mistral and Nvidia.

Model Description

• Developed by: llmware
• Model type: mistral
• Parameters: 12 billion
• Model Parent: mistralai/Mistral-Nemo-Instruct-2407
• Language(s) (NLP): English
• License: Apache 2.0
• Uses: General use
• Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website