Maryam Fazel

[AI at Meta @AIatMeta]

Today we published a technical report on Muse Glimmer, our 30B open-weight model built for agentic tasks on consumer hardware.

It runs at practical speeds on a Mac or PC with a single consumer GPU at 4-bit precision, and leads comparably-sized open models on tool use and multi-step planning.

Read about the model architecture, distillation recipe, quantization and more: https://t.co/H7n9qeDhxn

[Alexandr Wang @alexandr_wang]

1/ muse spark open is the most capable US open-weight model to date.

816B total params, 42B active. 1M-token context. natively multimodal. built for coding and agentic work like long-horizon tasks, hard software engineering, multi-step reasoning.

america! 🇺🇲

[Mark Zuckerberg @finkd]

Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.

[PyTorch @PyTorch]

Today @AIatMeta introduced Muse Glimmer, an open-weight, 30-billion-parameter model distilled from Meta’s Muse Spark for on-device agentic workflows. Alongside, ExecuTorch is adding end-to-end support for running Muse Glimmer on @NVIDIA GPUs and Macs with @Apple silicon.

Why ExecuTorch? ExecuTorch offers a smarter, native approach:
⚡ Build in PyTorch: Implement your model and decoding strategies right in PyTorch as you normally would
⚡ Seamless Export: Export directly to ExecuTorch when you're ready for deployment
⚡ Automated Optimization: The framework automatically handles backend-specific lowering (Triton on CUDA, MLX-native, or Metal on Apple silicon) and uses ahead-of-time compilation to optimize the full execution path end-to-end

Learn more: https://t.co/ABzlzreEJz

[AI at Meta @AIatMeta]

Introducing Muse Glimmer, an open-weight 30B-parameter model optimized for local, always-on agent workflows.

Muse Glimmer delivers strong performance on key agentic use cases and benchmarks compared with leading models in its size category, and is designed to run entirely on consumer hardware like a Mac or PCs with performant GPUs.

In keeping with our long tradition of sharing fundamental AI research, we’re releasing model weights under a permissive Apache 2.0 license.

🧵👇

[Alexandr Wang @alexandr_wang]

1/ big announcement today: we will be releasing an open weight version of muse spark 1.2 soon.

we also are releasing muse glimmer, a 30B agentic model with open weights under apache 2.0. muse glimmer can run on 24GB of VRAM without losing agentic reliability. 🧵

[Mark Zuckerberg @finkd]

Today we're also opening the weights for Muse Glimmer, a great 30B parameter dense model that can run locally. Soon we'll also release the weights for Muse Spark 1.2, our latest foundation model. Meta is a strong supporter of open source and I'm proud of these releases. Congrats to @alexandr_wang and the MSL team for all your great work on these models.

[Peifeng Wang @PeifengWang3]

How can we use #LLM to answer a complex question over a chart📊? Check out our new work, DOMINO, a dual-system for multi-step visual language reasoning😎!

📜arXiv: https://t.co/Y28Kdqtgs2
🧑‍💻code: https://t.co/uIIVmWQmkN

[AI at Meta @AIatMeta]

📚 New research from Meta AI — Shepherd is a language model specifically tuned to critique model responses & suggest refinements. It goes beyond the capabilities of untuned models to identify diverse errors & suggest improvements.

Read the paper ➡️ https://t.co/BtrTV0YEun

[Yann LeCun @ylecun]

This is huge: Llama-v2 is open source, with a license that authorizes commercial use!

This is going to change the landscape of the LLM market.
Llama-v2 is available on Microsoft Azure and will be available on AWS, Hugging Face and other providers

Pretrained and fine-tuned models are available with 7B, 13B and 70B parameters.

Llama-2 website: https://t.co/PKrrXgHdem
Llama-2 paper: https://t.co/aINNrXNhMb

A number of personalities from industry and academia have endorsed our open source approach: https://t.co/N7HwgW9Suh

[Armen Aghajanyan @ArmenAgha]

I’m excited to release our most recent work setting a new SOTA FID of 4.88 on text-to-image generation we call CM3Leon (pronounced chameleon)! https://t.co/KEGNFqFt3l

[AI at Meta @AIatMeta]

Today we're sharing new progress on our AI speech work. Our Massively Multilingual Speech (MMS) project has now scaled speech-to-text & text-to-speech to support over 1,100 languages — a 10x increase from previous work.

Details + access to new pretrained models ⬇️

[Moya Chen @moyapchen]

I'm proud to announce ROSCOE, our work using properties unique to step-by-step reasoning to better score generations from neural models! Thread motivating and contextualizing our work below 🧵👇🧵👇

[AI at Meta @AIatMeta]

ROSCOE is a first-of-its-kind suite of metrics for scoring step-by-step reasoning. By publishing this study we hope to provide a foundation that enables scalable systematic evaluation and benchmarking of new language models.

See the paper on arXiv ⬇️
https://t.co/3mUapPrNzn