Meta's First Open Model Now Runs Locally on Ollama
Ollama announced on August 10, 2026 that Muse Glimmer, Meta's newest open model and the first released by Meta Superintelligence Labs, is now available to run locally. Everything below is from that announcement, not from independent testing.
Transcript
Meta Superintelligence Labs just released its first open model, and today you can run it on your own machine.
Ollama says Muse Glimmer is Meta's newest open model, and the first from Meta Superintelligence Labs. It is thirty billion parameters and multimodal.
The announcement says it was built specifically for agent workloads that run locally, and can power coding agents like Claude Code and Codex, plus personal assistants.
Ollama says this is initial support, Apple Silicon only for now, with other platforms coming. A one point eight billion parameter encoder handles mockups, screenshots, and documents.
Inboxsmith helps small businesses handle calls and messages so nothing gets missed. Please like and subscribe for more news.
Sources
Every claim in this video comes from the top ranking coverage of this topic. The claims and where each one came from:
- Muse Glimmer, Meta's newest open model and the first released by Meta Superintelligence Labs, is now available on Ollama.(Ollama's official announcement)
- It's a 30B multimodal model purpose-built for agent workloads that run locally.(Ollama's official announcement)
- With Ollama, you can now use Muse Glimmer to power coding agent applications such as Claude Code, Codex, Pi and more, as well as long-running personal assistants such as OpenClaw and Hermes.(Ollama's official announcement)
- Muse Glimmer is currently available via initial support via Ollama's MLX engine on Apple Silicon.(Ollama's official announcement)
- Additional support and optimizations for Apple Silicon, NVIDIA, AMD, and other platforms will be available in the coming days.(Ollama's official announcement)
- Muse Glimmer's dedicated 1.8B-parameter perception encoder gives it native image understanding.(Ollama's official announcement)
- Image input tasks listed include building websites or applications from a drawing or mockup, computer use applications powered by screenshots, and reading documents, receipts, and charts.(Ollama's official announcement)
- The blog post is dated August 10, 2026, the same day as this story.(Ollama's official announcement)