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:

AI at Meta

@AIatMeta

We're building the future of personal superintelligence to help people create, connect, and achieve more in life.

加入 August 2018

372 正在關注 880.9K 粉絲

AI at Meta@AIatMeta

2026.10.19 19:33

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: