fauxpaslife/ Mellum2-Thinking-A2.5B-12B

1,106 1 month ago

Mellum 2 Thinking is a Mixture-of-Experts reasoning model (64 experts, 8 activated per token, 131,072-token context) that emits its chain of thought. (Q4_K_M)

1 model

Mellum2-Thinking-A2.5B-12B:latest
58acd52980fa • 8.2GB • 128K context window •
Text input • 1 month ago