Running Muse Glimmer Locally: Ollama Details 128K Context and Controllable Reasoning
mchiang0610 · x · 2026-08-10
Ollama's official blog provides a detailed guide on running Meta's open-source model, Muse Glimmer, locally. The 30B parameter model features a 128K+ context length and is purpose-built for local agent workloads.
Key Features & Usage:
- Coding & Assistant Support: Can power major coding tools like Claude Code, Codex, and GitHub Copilot, as well as personal assistant frameworks like OpenClaw via Ollama.
- Controllable Reasoning: Offers four levels of reasoning strength (low, medium, high, xhigh), allowing users to balance complex coding tasks with high response speeds.
- Underlying Optimizations: Ollama’s MLX engine provides support for DFlash and multi-token prediction (MTP), further boosting performance on Apple Silicon.
Related event: Meta Open-Sources 30B Muse Glimmer for On-Device Agents(108 posts)→
More from coding & agent
- Opus 5.5 + Three.js demo stuns with water physics, fish and blossoms — nikola_mr64990 · 2026-10-16
- Grok-built linear regression bot claims $508K PnL in 125 days on Polymarket — Roger_M_Taylor · 2026-10-16
- Karpathy's knowledge engine workflow: Claude Code turns raw notes into a self-updating wiki — nikola_mr64990 · 2026-10-16
- Sierra and Meta unveil Personal Agent Protocol with Zapier as launch partner — sujingshen · 2026-10-16
- ArcKit adds 102 AI-narrated short films for commands across 14 community overlays — mcraddock · 2026-10-16
- Personal agents live or die on chaining tasks, not single-task ability — sujingshen · 2026-10-16