Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

unsloth
/
Kimi-K2-Instruct-GGUF

Text Generation
Transformers
GGUF
deepseek_v3
unsloth
custom_code
fp8
conversational
Model card Files Files and versions
xet
Community
15
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

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

pinned
❤️ 🚀 2
#7 opened 8 days ago by
shimmyshimmer

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

❤️ 1
2
#15 opened 3 days ago by
krustik

Really appreciate the work you put into this.🤍

❤️ 🔥 3
1
#14 opened 5 days ago by
deep-div

Slow Token Generation on A100

2
#13 opened 6 days ago by
kingabzpro

144gb vram and 256gb ram

1
#12 opened 6 days ago by
fuutott

The correct eos_token_id value for Kimi-K2-Instruct

2
#11 opened 7 days ago by
anikifoss

Update the instructions on requirements

2
#10 opened 7 days ago by
segmond

Model link at the bottom is broken

1
#9 opened 8 days ago by
Ray9821

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

1
#5 opened 8 days ago by
qaraleza

Q5_K_M vs Q5_K_L vs Q5_K_XL

1
#4 opened 10 days ago by
ChuckMcSneed

Trouble running Q5_K_M With Llama.cpp

6
#3 opened 10 days ago by
simusid
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs