Show HN: Qwen3.6-35B-A3B on a 16 GB M1 Pro with SSD-streamed MoE

DeepSeek 4 Flash local inference engine for Metal and CUDA - andreaborio/ds4

22 points by andreaborio 96 days ago github.com 4 comments

Summary not yet generated for this article.

Loading more comments... ⌛

Scroll down to load more comments

No comments available.