title: Muse Glimmer 30B Agentic Demo
emoji: ✨
colorFrom: purple
colorTo: indigo
sdk: static
app_file: index.html
short_description: Safe tool-call demo for Muse Glimmer 30B
models:
- vcruz305/Muse-Glimmer-30B-Hermes-Agentic
Muse Glimmer 30B Hermes Agentic demo
This Space demonstrates vcruz305/Muse-Glimmer-30B-Hermes-Agentic. The live static interface can call a public, no-auth OpenAI-compatible endpoint serving the model. A self-hosted ZeroGPU Gradio implementation is included in app.py and is ready to activate when GPU hosting is available.
The interface demonstrates the behavior targeted by the fine-tune: answer directly when a tool is unnecessary, or propose one or two Hermes-style tool calls and stop. Tool calls are parsed and displayed, but never executed.
Safety and limitations
- The Space does not run commands, read files, browse the web, or perform destructive actions.
- Outputs are generated by research weights and may be incorrect or unsafe.
- The model is about 30B parameters and requires a 96 GB ZeroGPU allocation in BF16. The account that owns this Space is not currently eligible to create ZeroGPU Spaces, so the static client does not host the weights itself.
- The model card reports 16/20 on its simulated loop gate and 7/7 on a small native Hermes battery. These results are not a product certification.
API and MCP
The static demo accepts a public, no-auth OpenAI-compatible endpoint and sends requests directly from the visitor's browser. It does not accept or retain API keys. The included Gradio implementation exposes a generate endpoint and launches with MCP support once the Space is switched to Gradio with ZeroGPU hardware.