Local LLM model page

EXAONE Deep (7.8B)

LG AI Research reasoning model. Strong at math and coding reasoning. 200K 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 Deep (7.8B) run locally?

EXAONE Deep (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-deep-7.8b

Hugging Face repository: LGAI-EXAONE/EXAONE-Deep-7.8B-GGUF

reasoningstandard

Strengths

  • LG AI Research reasoning model. Strong at math and coding reasoning. 200K downloads.

Limitations

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

Best use cases

  • reasoning
  • standard

Benchmarks

Speed: 8/10

Quality: 7/10

Coding: 7/10

Reasoning: 8/10

Technical details

Developer: exaone

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2025-02