Available Model files:

  • EXAONE-4.0-1.2B.Q8_0.gguf


๐Ÿ“ข Please check out the guide from LG AI Research

Note

  • LGAI-EXAONE/EXAONE-4.0-32B model works with system prompt instructions.
  • The model's BOS token behavior was adjusted for GGUF compatibility.
  • This model was finetuned and converted to GGUF format using Unsloth.
Downloads last month
90
GGUF
Model size
1B params
Architecture
exaone4
Hardware compatibility
Log In to view the estimation

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for iassivarajuss/EXAONE-4.0-1.2B-Finetune-GGUF

Quantized
(27)
this model

Dataset used to train iassivarajuss/EXAONE-4.0-1.2B-Finetune-GGUF