←Search results

Search “Meta”

By relevance · Total 619 results Clear search

Tuesday

  3. AI at MetaSelected

    Meta releases Muse Glimmer technical report, a 30B open-weight model targeting agent tasks on consumer-grade hardware

    Meta releases the Muse Glimmer technical report, a 30B open-weight model targeting agent tasks on consumer-grade hardware. At 4-bit precision, the model can run at practical speeds on a single consumer-grade GPU in a Mac or PC, and it leads open-source models of the same scale in tool use and multi-step planning. The report covers the model architecture, distillation recipe, quantization, and more.

    Matched fieldsTitle

    #company#Papers/Research#Open-source ecosystem#English text is being prepared.
  4. Ma Dongxi NLP

    Meta releases technical report for Muse Glimmer 30B, an agentic model for consumer-grade hardware

    Meta has released the technical report for Muse Glimmer, a 30B open-weight model aimed at agentic tasks on consumer-grade hardware; it runs at 4-bit precision on a single consumer-grade GPU and leads open models of the same scale on tool calling and multi-step planning. The relayer adds that the model surpasses Qwen3.6-27B and Gemma4-31B on some metrics, is about 17GB after 4-bit quantization, targets devices with 24GB of VRAM, and uses DFlash speculative decoding to reach about 233 tokens/s on an RTX 5090, roughly 3.1 times faster than ordinary decoding.

    Meta has released the technical report for Muse Glimmer, a 30B open-weight model aimed at agentic tasks on consumer-grade hardware; it runs at 4-bit precision on a single consumer-grade GPU and leads open models of the same scale on tool calling and multi-step planning. The relayer adds that the model surpasses Qwen3.6-27B and Gemma4-31B on some metrics, is about 17GB after 4-bit quantization, targets devices with 24GB of VRAM, and uses DFlash speculative decoding to reach about 233 tokens/s on

    Matched fieldsTitle

    #hot-signal#Model releases#English text is being prepared.#Agents
  12. Unite.AI

    Meta Details Prometheus Supercomputer: Has Trained Muse Models, Plans to Scale to About 1 Million GPUs

    Meta's engineering team has published technical details of the Prometheus supercomputer, confirming that the first phase has trained the Muse family of foundation models (including Muse Wonder) and that it plans to scale the system to about 1 million GPUs. The cluster is located in New Albany, Ohio, currently consists of hundreds of thousands of GPUs, and runs as a single machine; Muse Wonder achieved pretraining goodput above 85% and reinforcement learning above 90%. Meta also disclosed two platforms—Catalina based on NVIDIA GB200 NVL72 and Clemente based on GB300 NVL72—as well as the upcoming Vera Rubin NVL72 platform.

    Meta's engineering team has published technical details of the Prometheus supercomputer, confirming that the first phase has trained the Muse family of foundation models (including Muse Wonder) and that it plans to scale the system to about 1 million GPUs. The cluster is located in New Albany, Ohio, currently consists of hundreds of thousands of GPUs, and runs as a single machine; Muse Wonder achieved pretraining goodput above 85% and reinforcement learning above 90%. Meta also disclosed two pla

    Matched fieldsTitle

    #hot-signal#Industry news#English text is being prepared.#English text is being prepared.
  14. Fireworks AI

    Meta's open-weight model Muse Spark Open launches on Fireworks: 816B parameters, 1M context

    Meta's open-weight model Muse Spark Open is available on Fireworks from day one of launch. It is an 816B-parameter MoE model that activates 42B parameters per token, with a 1M-token context window, targeting long-horizon coding and agentic tasks. Fireworks says it ranks first among 75 models on Vals AI's Harvey legal agent benchmark with 25.4%, nearly 4 times that of Claude Opus 5 (6.7%); on the Rogo Big Finance Bench it surpasses Claude Opus 5.5 at every difficulty level. Fireworks validated the weights with its own production stack, scoring 91.1% on AIME26, 89.7% on GPQA Diamond, and 84.3% on SWE-bench Verified, and reproduced consistent results with SGLang.

    Meta's open-weight model Muse Spark Open is available on Fireworks from day one of launch. It is an 816B-parameter MoE model that activates 42B parameters per token, with a 1M-token context window, targeting long-horizon coding and agentic tasks. Fireworks says it ranks first among 75 models on Vals AI's Harvey legal agent benchmark with 25.4%, nearly 4 times that of Claude Opus 5 (6.7%); on the Rogo Big Finance Bench it surpasses Claude Opus 5.5 at every difficulty level. Fireworks validated th

    Matched fieldsTitle

    #editorial#Product updates#Model releases#English text is being prepared.

Monday

  1. Shao Meng

    pstack adds a formal verification meta-skill

    pstack v0.15.27 adds /create-formal-verification-skill, a meta-skill that automatically generates a customized verification skill and a matching verification suite based on the characteristics of the system to be verified. For example, it generates a TLA+-based approach for state machines and concurrent behavior, and a Kani-based approach for Rust undefined behavior. The feature is still in beta, and the author has already found several bugs while using it to model their own code with TLA+. poteto believes that the two historical bottlenecks of modeling and spec synchronization are well suited to being taken over by LLMs, and that formal verification can give agents strong feedback that is "mathematically impossible to violate."

    pstack v0.15.27 adds /create-formal-verification-skill, a meta-skill that automatically generates a customized verification skill and a matching verification suite based on the characteristics of the system to be verified. For example, it generates a TLA+-based approach for state machines and concurrent behavior, and a Kani-based approach for Rust undefined behavior. The feature is still in beta, and the author has already found several bugs while using it to model their own code with TLA+. pote

    Matched fieldsTitle

    #hot-signal#Product updates#Agents#English text is being prepared.