Muse Glimmer 30B

At a glance

What Muse Glimmer 30B does

Vision, Tool use, Agentic local use, Apache 2.0 licence, Single-GPU inference

Best for

Always-on local agents running on a single GPU

Works well with

Conflicts & caveats

• Trae's built-in model menu may not include Muse Glimmer 30B — Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
• Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but Muse Glimmer 30B is not in the supported model list.
• Kiro's spec mode is tuned for Claude models — Muse Glimmer 30B may work but spec-driven flows are best with Claude.
• Cursor's built-in model menu may not include Muse Glimmer 30B — verify it's available in your Cursor model picker.
• OpenAI Codex (VS Code) is tied to OpenAI's hosted GPT-5 and Codex models — Muse Glimmer 30B is not selectable inside this integration.
• Gemini CLI is locked to Google Gemini models — your LLM is Muse Glimmer 30B.
• Claude Code only works with Claude models — your LLM is Muse Glimmer 30B.
• Devin uses Cognition's proprietary model internally — your selected Muse Glimmer 30B will be ignored.
• OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Muse Glimmer 30B will be ignored.
• Jules runs Gemini models internally — your selected Muse Glimmer 30B will be ignored.
• The Claude Code SDK is tuned for Claude models — Muse Glimmer 30B may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
• Lovable uses a fixed internal model — your selected Muse Glimmer 30B will be ignored.
• Replit Agent 3 uses its own model selection internally — your selected Muse Glimmer 30B will be ignored.