Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
m-i
/
K2-Think-mlx-8Bit
like
0
Text Generation
Transformers
Safetensors
MLX
English
qwen2
conversational
text-generation-inference
8-bit precision
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
K2-Think-mlx-8Bit
/
config.json
Commit History
Upload config.json with huggingface_hub
21b5e22
verified
m-i
commited on
Sep 10, 2025
m-i
commited on
