A new version of the DeepSeek-V4.1-Flash-1017 model has been released, optimized for use on Macs with 128GB of RAM. This iteration, referred to as "Sushi-STQ-1.75bpw," is available via a Hugging Face link. The release also mentions "Modality Aware Capacity Scaling" in relation to the model's capabilities. AI
IMPACT Provides a specialized model for Mac users with high RAM, potentially improving local AI inference performance on that hardware.
RANK_REASON This is a specific model release for a particular hardware configuration, not a frontier model release from a major lab.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →