Muse Glimmer 30B

Settings

System prompt Background instructions that steer how the model responds. Thinking level Controls reasoning depth. Max new tokens: Maximum length of the reply. Average speed is ~20 tok/s. ZeroGPU Spend: s Initial quota requested per query. Uses remaining quota if the answer is longer. Enable DFlash Acceleration

Advanced settings

Temperature: Higher is more random and creative; 0 is deterministic. Top-p: Keep the smallest set of tokens whose probabilities sum to this. Top-k: Consider only the k most likely tokens (0 turns it off). Repetition penalty: Higher discourages repeating words; 1 turns it off.

Muse Glimmer 30B

Start the conversation below.