Meta 与 Apple 合作：816B 开放权重模型 Muse Spark Open 可在两台 Mac Studio 上运行
Meta 放出 816B 的开源权重模型，Apple 帮忙适配 MLX，两台 Mac Studio 就能跑，工具调用测试拿了 89.2 分，做编程智能体的可以看看。
Meta 发布 816B 参数的开放权重模型 Muse Spark Open，Apple 为其 MLX 框架做了适配。模型采用 MoE 架构，256 个专家中每个 token 只激活 8 个、约 42B 参数，降低了单步显存读取量。完整模型即使 4-bit NVFP4 量化也需至少 700GB 显存，两台各配 512GB 统一内存的 M5 Ultra Mac Studio 可以装下。在 MCP-Atlas 工具调用测试上得分 89.2，定位是编程智能体。许可允许免费商用，但需标注“Built with Muse Spark Open”，年 API 收入超 2000 万美元的厂商需另与 Meta 签约。
After years of rivalry, Meta and Apple join hands to deliver open-weight AI to the Mac.
Meta released the weights for Muse Spark Open, an 816B-parameter model that runs on 2 linked Mac Studios.
Apple tuned the release for its MLX framework. Only 42B parameters fire per token because the model routes each token to 8 of 256 experts, so every step reads a small slice of memory.
Holding the whole model is the hard part, since the 4-bit NVFP4 version needs at least 700GB of GPU memory.
Each M5 Ultra Mac Studio gives its GPU up to 512GB of unified memory, so 2 machines hold the model while 1.2TB/s of bandwidth feeds each token.
On the benchmarks, Muse Spark Open does top the MCP-Atlas tool-use test at 89.2, which suits the coding agents Meta built it for.
The license allows free commercial use but requires a “Built with Muse Spark Open” label, plus a separate Meta deal for API model sellers with over $20M in 12-month revenue.
Apple hasn’t priced the 512GB Mac Studio, and a cluster of 4 machines with 256GB each costs roughly $38,000.
