Rewards Hub UnslothAI has launched a 4-bit MLX-optimized version of its DGEMMA 4-31B model, tailored for Apple Silicon. This new release promises rapid inference speeds on all M-series Macs, utilizing around 20GB of RAM efficiently. The model is designed to enhance multimodal and visual performance, supporting a 256K context length and native function calling capabilities.
UnslothAI Unveils 4-bit MLX Optimized DGEMMA 4-31B for Apple Silicon
Disclaimer: The content provided on Phemex News is for informational purposes only. We do not guarantee the quality, accuracy, or completeness of the information sourced from third-party articles. The content on this page does not constitute financial or investment advice. We strongly encourage you to conduct you own research and consult with a qualified financial advisor before making any investment decisions.