This is a quantized version of the EXAONE-4.0.1-32B model of LGAI-EXAONE, processed by the imatrix quantization technology of llama.cpp, which can run efficiently under different hardware conditions. It provides a variety of quantization options from BF16 to extremely low bit rates, suitable for various memory and performance requirements.

Natural Language ProcessingGguf

EXAONE-4.0-1.2B is a 1.2B parameter language model released by LGAI-EXAONE, offering multiple quantization versions to meet different hardware requirements.

Natural Language ProcessingGguf

The quantized version of the EXAONE-4.0-32B model by LGAI-EXAONE, quantized using the llama.cpp tool, aiming to provide more flexible usage options for users with different hardware conditions.

Natural Language ProcessingGguf

EXAONE 4.0 is a multilingual large language model that integrates non-inference mode and inference mode, supporting English, Korean, and Spanish, and has the ability to invoke agent tools.

Natural Language ProcessingTransformersMultiple Languages

The EXAONE 4.0 model integrates non-inference mode and inference mode, combining the excellent usability of EXAONE 3.5 with the advanced inference capabilities of EXAONE Deep. It supports three languages: English, Korean, and Spanish, providing stronger support for intelligent applications.

Natural Language ProcessingTransformersMultiple Languages

EXAONE 4.0 is a multi-functional large language model that integrates non-reasoning and reasoning modes, supports English, Korean, and Spanish, and has the ability to use agent tools.

Natural Language ProcessingTransformersMultiple Languages

LGAI's EXONE series reasoning model, featuring new matrix and extreme quantization technologies, equipped with a 32k context window, focusing on deep thinking and reasoning tasks.

Natural Language ProcessingGgufMultiple Languages

This is the quantized version of LGAI-EXAONE's EXAONE-Deep-2.4B model, quantized using llama.cpp, supporting English and Korean text generation tasks.

Natural Language ProcessingGgufMultiple Languages

The EXAONE Deep series models excel in reasoning tasks such as mathematics and programming. This model is the 4-bit AWQ quantized version with 2.4 billion parameters

Natural Language ProcessingTransformersMultiple Languages