unsloth
/

Kimi-K2-Instruct-GGUF

Text Generation

Model card Files Files and versions

Resources

View closed (4)

New updates: Correct system prompt, Tool calling, more fixes & llama.cpp!

#7 opened 9 days ago by

Amazing quality in such low Q4 on 2014 ANCIENT Xeon CPU with just shy 582Gb RAM

#15 opened 4 days ago by

Really appreciate the work you put into this.🤍

#14 opened 6 days ago by

Slow Token Generation on A100

#13 opened 7 days ago by

144gb vram and 256gb ram

#12 opened 7 days ago by

The correct eos_token_id value for Kimi-K2-Instruct

#11 opened 8 days ago by

Update the instructions on requirements

#10 opened 8 days ago by

Model link at the bottom is broken

#9 opened 9 days ago by

Good llama.cpp -ot offloading parameter for 24 GB / 32 GB cards?

#5 opened 9 days ago by

Q5_K_M vs Q5_K_L vs Q5_K_XL

#4 opened 11 days ago by

Trouble running Q5_K_M With Llama.cpp

#3 opened 11 days ago by