# Mac Studio Published articles for Mac Studio. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Meta releases 816B-parameter Muse Spark Open for coding and agent work DevFeed: [Meta releases 816B-parameter Muse Spark Open for coding and agent work]() Original publisher: [Read original article]() Author: Duncan Riley Published: 2026-10-15T22:20:54Z Content type: news Language: en Sources: [SiliconANGLE]() Topics: [gpt-oss](), [Frontier AI](), [agent orchestration](), [agent to agent communication](), [cursor]() Tags: [agent](), [ai](), [amazon-web-services](), [api](), [apple](), [artificial-intelligence](), [coding](), [davinci-resolve](), [fireworks-ai](), [glm-5-3](), [google](), [groq](), [hugging-face](), [ice-cubes](), [inference-providers](), [inkling](), [jobbench](), [kimi-k3](), [long-running](), [m5-ultra](), [mac-studio](), [mastodon](), [mcp-atlas](), [meta](), [meta-model-api](), [meta-platforms](), [meta-superintelligence-scaling-framework](), [microsoft](), [mlx](), [model](), [model-context-protocol](), [muse-code](), [muse-glimmer](), [muse-model-license](), [muse-spark](), [muse-spark-1-2](), [muse-spark-open](), [news](), [open-weights](), [platforms](), [release](), [the-latest](), [top-story-3]() ### AI overview Meta released open weights for Muse Spark Open, an 816-billion-parameter model designed for coding and long-running agent work. The report describes its multimodal inputs and million-token context window, tests involving coding tasks and tool use, and license terms for developers and hosted providers. Meta says it scored strongly on an agent tool-use benchmark, while Chinese open models scored higher on the coding benchmark cited. ### Source excerpt Meta Platforms Inc. today released open weights for its Muse Spark artificial intelligence model, which had been proprietary since its April debut. The release, called Muse Spark Open, is built for coding and long-running agent work. Meta describes it as the most capable open-weight model to come out of a U.S. lab so far. Only [...] The post Meta releases 816B-parameter Muse Spark Open for coding and agent work appeared first on SiliconANGLE. ## Meta launches an open-weight AI model that runs on Macs DevFeed: [Meta launches an open-weight AI model that runs on Macs]() Original publisher: [Read original article]() Author: Lucas Ropek Published: 2026-10-15T20:04:53Z Content type: news Language: en Sources: [TechCrunch | AI News & Artificial Intelligence]() Topics: [gpt-oss](), [Local AI](), [lunar foundation model]() Tags: [ai](), [ai-model](), [apple](), [cost](), [evaluation](), [m5-ultra](), [mac](), [mac-studio](), [memory](), [meta](), [multimodal](), [muse](), [muse-code](), [open-weight-ai](), [performance](), [ram]() ### AI overview Meta launched Muse Spark Open, an open-weight multimodal model designed to run locally on Macs. It has 816 billion parameters and a one-million-token context window, and Meta says it is built for complex coding tasks and agentic workflows. Running it locally requires at least 1 terabyte of RAM; Meta also says it is available through several API platforms. ### Source excerpt Meta and Apple have teamed up for the launch of the social media giant's newest model, Muse Spark Open, which will run locally on Apple silicon. ## Local and Distributed Large LLM Inference with MLX and RDMA on Mac Studio DevFeed: [Local and Distributed Large LLM Inference with MLX and RDMA on Mac Studio]() Original publisher: [Read original article]() Published: 2026-10-15T00:00:00Z Content type: article Language: en Sources: [Apple Machine Learning Research]() Topics: [MLX](), [AI Infrastructure](), [rdma](), [On-device AI]() Tags: [apple-silicon](), [fine-tuning](), [gpu](), [inference](), [llm-inference](), [mac](), [mac-studio](), [memory-architecture](), [rdma](), [unified-memory-architecture]() ### AI overview The article benchmarks local and distributed LLM inference using MLX on Apple silicon Mac Studio systems. It describes pipeline and tensor parallelization over RDMA via Thunderbolt, compares model performance across M3 Ultra and M5 Ultra machines, and explains how this setup can run large models locally for agentic AI tools. ### Source excerpt MLX on Mac with Apple silicon lets AI researchers and developers experiment locally with the latest models and methods in a private environment. The open-source array framework leverages the unified memory architecture of Apple silicon, enabling anyone to run new inference and fine-tuning methods on their own hardware and explore other AI techniques. In a previous post, we highlighted the advantages of the M5 architecture and its GPU Neural Accelerators. ## Apple launches new Mac Mini and Mac Studio models for on-device AI DevFeed: [Apple launches new Mac Mini and Mac Studio models for on-device AI]() Original publisher: [Read original article]() Author: Tech Desk Published: 2026-09-23T07:19:14Z Content type: news Language: en Sources: [Technology | The Indian Express]() Topics: [Artificial Intelligence](), [Mac Mini](), [On-device AI](), [Hardware](), [Computing](), [idc](), [Microsoft](), [iphone]() Tags: [ai](), [apple](), [apple-intelligence](), [hardware](), [localized-ai-workloads](), [m5-max-chip](), [m5-pro-chip](), [mac](), [mac-mini](), [mac-mini-m6](), [mac-studio](), [mac-studio-m5-ultra](), [memory](), [on-device](), [on-device-ai](), [openclaw-ai-agent](), [performance](), [rdma-over-thunderbolt](), [tech](), [technology](), [technology-tech](), [unified-memory-architecture]() ### AI overview Apple has released new Mac Mini and Mac Studio models designed to run AI workloads locally. The article discusses their chips, memory, networking, enterprise positioning, and potential use as an alternative to some cloud infrastructure. ### Source excerpt Apple's new Mac Mini M6, Mac Mini M5 Pro, Mac Studio M5 Max, and Mac Studio M5 Ultra are now available, bringing faster performance and more memory for powerful on-device AI.