Meta opens Muse Spark Open weights, with cloud and Mac support
What happened
On October 15, vLLM said it worked with Meta to give Muse Spark Open day-one inference and LoRA RL support, with Together AI and Modal launching at the same time. The model targets coding and long-horizon agent tasks: 816B total parameters, 42B active per token, a 1M-token context and native multimodality. Reports differ on timing, with earlier coverage saying weights landed October 16 and later coverage saying October 15. On October 16, reports confirmed the weights are on Hugging Face under the Muse Model License, with Baseten and OpenRouter serving inference; OpenRouter lists $1.25 and $4.25 per million input and output tokens. The Verge says Meta worked with Apple for months to run the model on two M5 Ultra Mac Studios via the latest MLX framework, and TechCrunch confirmed Mac local support. The model is in Agent Arena for testing, with scores not yet published.
Written by AI from the coverage · updated 38 minutes ago
Developments
- Oct 16 04:03 · 1 reportMeta's Muse Spark Open goes live on Together AIAI HOT · Products
- Oct 16 04:03 · 1 reportMeta releases Muse Spark Open weights, with token-priced shared endpoint on ModalAI HOT · Products
- Oct 16 03:02 · 1 reportvLLM ships day-one support for Muse Spark OpenAI HOT · Products
- Oct 16 02:19 · 1 reportMeta Muse Spark Open 上架 Agent Arena，开放实测且评分即将公布AI HOT · Models
- Oct 16 01:27 · 7 reportsMeta releases Muse Spark Open weights, runs locally on two Mac StudiosHacker News front page
Coverage
Follow the reports to see the story from different sides.
- TechCrunch · AIMeta launches an open-weight AI model that runs on Macs
Meta 发布开放权重模型 Muse Spark Open，拥有 816 billion 参数和 1 million token 上下文窗口，支持在 Mac 本地运行。
- AI HOT · ProductsPickMeta's Muse Spark Open goes live on Together AI
Meta's open-weight model Muse Spark Open launched on Together AI today, aimed at long-running agentic coding workflows. It offers a 1M-token context window and supports sub-agent collaboration, tool calls, computer use and web browsing, and accepts text, image, audio and audio-video input.
- AI HOT · ProductsPickMeta releases Muse Spark Open weights, with token-priced shared endpoint on Modal
Meta released the Muse Spark Open weights, and Modal Auto Endpoints now serves a shared endpoint billed per token. The model targets agentic coding and long-horizon tasks, with native multimodal understanding and a 1M-token context window. It handles code writing and debugging, multi-step planning, sequential tool calls and recovery from failures in long workflows.
- AI HOT · ProductsPickvLLM ships day-one support for Muse Spark Open
vLLM worked with Meta Superintelligence Labs to add day-one inference and LoRA RL support for Muse Spark Open. The open-weight MoE model targets long-horizon agentic coding workflows, with 816B total parameters, 42B activated per token, a 1M context window, and image, video and audio input. vLLM runs it across several hardware platforms and offers prebuilt images, so deployers can serve the model without waiting for the usual package merge.
- The DecoderPickMeta answers Qwen, GLM and Kimi with open-weight Muse Spark Open
Meta released Muse Spark Open, an open-weight model for coding and agent tasks with 816 billion total parameters and 42 billion active, a context window up to 1 million tokens, and text, image, video and audio input. Meta says it leads some open models on agent, knowledge reasoning and multimodal benchmarks, while trailing some competitors on coding.
- AI HOT · ModelsMeta Muse Spark Open 上架 Agent Arena，开放实测且评分即将公布
Arena 宣布 Meta 的 Muse Spark Open 已进入 Agent Arena，用户可实测，评分即将公布。该模型拥有 816B 总参数、42B 激活参数和 1M token 上下文窗口，支持原生多模态。
- The Verge · AIPickMeta and Apple team up to run Muse AI models better on Mac
Meta released Muse Spark Open with open weights and worked with Apple to run it through the latest MLX framework on two Apple M5 Ultra Mac Studios. Meta says the model is natively multimodal, has 816 billion total parameters, and handles long-horizon tasks, complex software engineering and multi-step reasoning. The two companies worked together for months, and Apple published a technical article covering MLX, Muse Spark Open and two other open models.
- AI HOT · ProductsPickMeta releases open-weight Muse Spark Open, live on OpenRouter
Meta released the open-weight Muse Spark Open, now available on OpenRouter and positioned as the strongest US open-weight model for coding and agent work. It has 816B total parameters, 42B active, a 1M token context window and native multimodal input covering images, video, audio and PDF. OpenRouter prices it at $1.25 per million input tokens and $4.25 per million output tokens.
- AI HOT · ModelsPickMeta releases Muse Spark Open, an open-weight model with 816B total parameters and a 1M-token context
Meta released Muse Spark Open, an open-weight model with 816B total parameters, 42B active parameters and a 1M-token context window. The weights are available on Hugging Face under the Muse Model License.
- Hacker News front pagePickMeta releases Muse Spark Open weights, runs locally on two Mac Studios
Meta released the Muse Spark Open model weights with native multimodal support, 816B total parameters, 42B active parameters and a 1M-token context window, aimed at coding and agent tasks. The weights run locally on two Mac Studios.
- AI HOT · ModelsPickMeta releases open-weight Muse Spark Open, with Baseten serving it on day one
Meta released the Muse Spark Open weights, and Baseten is serving the model the same day through Model APIs and Dedicated Inference, aimed at coding agent workflows. Baseten's NVFP4 deployment cuts the weight footprint from about 1.6 TB to 540 GB, freeing VRAM for concurrent agent sessions.
Heat over time
Heat now 47·Comparable peak 47（Oct 16 05:00）·Comparable change over 24 hours –
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.