Muse Spark Open: 816B MoE on Two Mac Studios at 1M Context
Meta's 816B-param, 42B-active multimodal MoE runs on two M5 Ultra Mac Studios with 1M context, Helion kernel speedups, and open weights via MLX, vLLM, and SGLang.
1 post
Meta's 816B-param, 42B-active multimodal MoE runs on two M5 Ultra Mac Studios with 1M context, Helion kernel speedups, and open weights via MLX, vLLM, and SGLang.