Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
danielhanchenย 
posted an update 5 days ago
Post
8331
You can now run MiniMax-2.5 locally! ๐Ÿš€
At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat.

Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/minimax-2.5
GGUF: unsloth/MiniMax-M2.5-GGUF

How bad is the precision loss on the Q2_K_XL quants? I can run that with full GPU offload but I usually dont run lower than Q4, broadly.