ME News reports that on April 11 (UTC+8), UnslothAI recently released a native 4-bit MLX-optimized version of the DGEMMA 4-31B model. Designed specifically for Apple Silicon, this version reportedly delivers extremely fast inference speeds across all M-series Macs while maintaining efficient memory usage (approximately 20GB RAM). Additionally, the model offers strong multimodal and visual performance, supporting a full 256K context length and native function calling capabilities. (Source: InFoQ)
UnslothAI Launches 4-bit MLX Optimized DGEMMA 4-31B for Apple Silicon
KuCoinFlashShare
Summary
On-chain news: On April 11 (UTC+8), UnslothAI launched a 4-bit MLX-optimized DGEMMA 4-31B model for Apple Silicon. The model runs efficiently on M-series Macs with approximately 20GB of RAM and supports a 256K context length. Crypto news: It also delivers strong multimodal performance and native function calling.
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information.
Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.