Local LLM model page

EXAONE 3.5 (7.8B)

LG AI bilingual model (EN/KR). Strong performance at 7.8B. 118K downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
7.8B
Minimum RAM
8 GB
Model size
4.7 GB
Quantization
Q4_K_M

Can EXAONE 3.5 (7.8B) run locally?

EXAONE 3.5 (7.8B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q4_K_M as the default quantization, with at least 8 GB RAM.

Search term for LM Studio or compatible runtimes: exaone-3.5-7.8b-instruct

Hugging Face repository: LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct-GGUF

chatstandardgeneral

Strengths

  • LG AI bilingual model (EN/KR). Strong performance at 7.8B. 118K downloads.

Limitations

  • Performance depends heavily on quantization, RAM bandwidth and runtime support.

Best use cases

  • chat
  • standard
  • general

Benchmarks

Speed: 8/10

Quality: 7/10

Coding: 6/10

Reasoning: 7/10

Technical details

Developer: exaone

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-12