EXAONE 3.5 7.8B Instruct

Name: EXAONE 3.5 7.8B Instruct
Author: LG AI Research

by LG AI ResearchEXAONE

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released December 202433K context≈ 24,576 words7.8B params

A compact bilingual specialist with genuine strength in both English and Korean, EXAONE 3.5 7.8B punches above its weight class for instruction-following tasks. It handles technical and conversational prompts with reasonable fluency, though its 7.8B parameter count means complex multi-step reasoning can hit a ceiling. Built with a practical, instruction-tuned disposition rather than raw capability.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Instruction Following

Strong

Multilingual

EXAONE 3.5 7.8B Instruct

by LG AI ResearchEXAONE

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released December 202433K context≈ 24,576 words7.8B params

A compact bilingual specialist with genuine strength in both English and Korean, EXAONE 3.5 7.8B punches above its weight class for instruction-following tasks. It handles technical and conversational prompts with reasonable fluency, though its 7.8B parameter count means complex multi-step reasoning can hit a ceiling. Built with a practical, instruction-tuned disposition rather than raw capability.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Instruction Following

Strong

Multilingual

Glossary

BilingualA model trained to understand and generate text in two languages, in this case Japanese and English.Instruction-FollowingThe ability of a model to understand and execute specific tasks or commands given in natural language prompts.Instruction-TunedA model fine-tuned on instruction-response pairs so it follows user prompts more reliably.Multi-Step ReasoningThe ability to break down complex problems into smaller steps and solve them sequentially, rather than jumping directly to an answer.Parameter CountThe total number of adjustable weights in a model; more parameters generally mean more capacity to learn, but also require more computing power.ReasoningThe model's ability to work through multi-step logical problems and provide justified answers rather than just pattern-matching.

EXAONE 3.5 7.8B Instruct

Capabilities

EXAONE 3.5 7.8B Instruct

Capabilities

Benchmark Scores

Use Case Fit

Glossary