OPEN MODEL · TOOL USE · SAFE SIMULATION

Muse Glimmer 30B

Explore the Hermes Agentic fine-tune: direct answers when no tool is needed, concise tool proposals when one is.

View model card ↗
Nothing is executed. Tool calls are parsed and displayed. This page never runs shell commands, reads files, or performs web searches.
NO AUTH

Requests go directly from your browser to /v1/chat/completions. The server must allow browser CORS. Do not paste credentials; this demo intentionally has no API-key field.

Advanced settings

Assistant response

Run an example to see the model response.

Proposed tool calls

0 executed 
[]

SERVE THE MODEL

Connect the GGUF with llama.cpp

The FP16 checkpoint needs well over 56 GB. On a 24 GB GPU, the model author recommends the Q4_K_M GGUF, DFlash off, and a recent Muse-aware llama.cpp build. Expose it only through infrastructure you trust. 

llama-server \
  -m Muse-Glimmer-30B-Hermes-Agentic-Q4_K_M.gguf \
  -a muse-glimmer-30b --host 0.0.0.0 --port 8084 \
  -ngl 99 -c 32768 -np 1 --jinja \
  --temp 0.6 --top-p 0.95 --top-k 64