EXAONE 3.5 2.4B
LG AI's edge-tier EXAONE. Strong Korean / English. Research-only license.
Overview
LG AI's edge-tier EXAONE. Strong Korean / English. Research-only license.
Family & lineage
How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.
Strengths
- Korean depth
- Edge deployable
Weaknesses
- Research license
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 1.6 GB | 3 GB |
Get the model
HuggingFace
Original weights
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of EXAONE 3.5 2.4B.
Frequently asked
What's the minimum VRAM to run EXAONE 3.5 2.4B?
Can I use EXAONE 3.5 2.4B commercially?
What's the context length of EXAONE 3.5 2.4B?
Source: huggingface.co/LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify EXAONE 3.5 2.4B runs on your specific hardware before committing money.