EXAONE 4.5 33B

Overview

LG AI Research's multimodal Korean flagship: a 33B model with 256k context that lands in the top 10 of the Artificial Analysis Intelligence Index.

When to pick this model

• Korean-language production workloads
• Bilingual EN/KR multimodal applications
• Vision tasks needing a compact 33B footprint
• Long-context multimodal analysis

VRAM requirements by quantization

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Strengths

• 262k context in a 33B model
• Integrated vision capabilities at this scale
• Strong Korean and English performance
• Top-10 placement on independent intelligence benchmarks

Limitations

• Around 20 GB VRAM at Q4
• EXAONE license requires review for commercial use
• Smaller English-focused community than Llama or Qwen

Architecture & training

Architecture: Dense · 33B · EXAONE 4.5 · LG AI Research · integrated vision

Training: LG AI Research — Korean+English corpus, multimodal vision added, 262k ctx.

Quick start

ollama run exaone4.5:33b

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.