LGAI-EXAONE
/

EXAONE-4.0-32B

Text Generation

Model card Files Files and versions

Resources

View closed (6)

Why does the EXAONE-4.0 chat_template strip <think> with [:9] instead of [:7]?

#13 opened 4 months ago by

question regarding the reasoning feature.

#12 opened 5 months ago by

Are there any plans for 8B or 14B models like Qwen3?

#11 opened 6 months ago by

llama.cpp thinking mode support

#10 opened 7 months ago by

AWQ or GPTQ quantization?

#8 opened 8 months ago by

Really appreciate the work you put into this.🤍

#7 opened 8 months ago by

This model is not much better than qwen3 32b for writing code

#4 opened 8 months ago by