Meta publishes a technical report on Muse Glimmer, its 30 billion parameter open weight model for running agents on a single consumer GPU
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:
Context
A capable agent model that runs locally keeps personal data on the device, and Meta's report explains how it shrank and trained such a model.
This is a technical report on a model Meta already released, not a new model. Meta introduced Muse Glimmer with open weights under Apache 2.0 in August, and the benchmark comparisons are Meta's own.
Deep dive
On October 19, AI at Meta posted that it published a technical report on Muse Glimmer, its 30B open weight model built for agentic tasks on consumer hardware. It said the model 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. It said the report covers the architecture, distillation recipe and quantization.
The report's abstract describes a 30 billion parameter language model with a perception encoder that takes text and images and outputs text, trained on data in over a hundred languages. Meta claims state of the art results for its size on agentic benchmarks against Gemma4 31B and Qwen3.6 27B.
Meta's August launch post said that at full precision the model would need over 55 GB of memory, and that quantization to about 4 bits shrinks the language model to under 20 GB, leaving room for memory, the vision encoder and a speculative decoding drafter within 24 or 32 GB. The Hugging Face model card says it was distilled from Muse Spark and lists a 131,072 token context window.
The report adds detail on how the model was built rather than new capabilities, so its main value is for researchers and developers running local agents.
What to expect next
Watch whether outside developers reproduce Meta's agentic benchmark results on consumer hardware, and how Muse Glimmer compares with new small models from Google and Alibaba's Qwen team. The distillation recipe in the report could be reused by others to build small agent models. Also watch whether Meta ships Muse Glimmer inside its own apps for on device features, and whether it releases a newer local model.