EXAONE 4.5

pip install git+https://github.com/nuxlear/transformers.git@add-exaone4_5

trtllm-serve LGAI-EXAONE/EXAONE-4.5-33B \
    —tp_size 2 \
    —port 8000 \
    —reasoning_parser qwen3

uv pip install git+https://github.com/lkm2835/vllm.git@add-exaone4_5
uv pip install git+https://github.com/nuxlear/transformers.git@add-exaone4_5

vllm serve LGAI-EXAONE/EXAONE-4.5-33B \
    --served-model-name EXAONE-4.5-33B \
    --port 8000 \
    --tensor-parallel-size 2 \
    --max-model-len 262144 \
    --reasoning-parser qwen3 \
    --enable-auto-tool-choice \
    --tool-call-parser hermes \
    --limit-mm-per-prompt '{"image": 64}' \
    --speculative_config '{
        "method": "mtp", 
        "num_speculative_tokens": 3
    }'

uv pip install 'git+https://github.com/lkm2835/sglang.git@add-exaone4_5#subdirectory=python&egg=sglang[all]'
uv pip install git+https://github.com/nuxlear/transformers.git@add-exaone4_5

python -m sglang.launch_server \
    --model-path LGAI-EXAONE/EXAONE-4.5-33B \
    --served-model-name EXAONE-4.5-33B \
    --port 8000 \
    --tp-size 2 \
    --mem-frac 0.81 \
    --reasoning-parser qwen3 \
    --tool-call-parser hermes \
    --speculative-algorithm EAGLE \
    --speculative-num-steps 3 \
    --speculative-eagle-topk 1 \
    --speculative-num-draft-tokens 4

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="EMPTY",
)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image_url",
                "image_url": {
                    "url": "https://github.com/Aim-Highest/EXAONE-4.5/blob/main/assets/exaone45_input2.png?raw=true",
                },
            },
            {
                "type": "text",
                "text": "How much larger is the model released in winter 2025 compared with the one released in summer 2024?",
            },
        ]
    }
]

response = client.chat.completions.create(
    model="EXAONE-4.5-33B",
    messages=messages,
    max_tokens=32768,
    temperature=1.0,
    top_p=0.95,
    presence_penalty=1.5,
    extra_body={
        "chat_template_kwargs": {
            "enable_thinking": True,  # default: True
        }
    }, 
)
print(response)

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="EMPTY",
)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image_url",
                "image_url": {
                    "url": "https://github.com/Aim-Highest/EXAONE-4.5/blob/main/assets/exaone45_input1.jpg?raw=true",
                },
            },
            {
                "type": "text",
                "text": "What dish is the person preparing, and how is it made?",
            },
        ]
    }
]

response = client.chat.completions.create(
    model="EXAONE-4.5-33B",
    messages=messages,
    max_tokens=32768,
    temperature=1.0,
    top_p=0.95,
    presence_penalty=1.5,
    extra_body={
        "chat_template_kwargs": {
            "enable_thinking": False,  # default: True
        }
    }, 
)
print(response)

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="EMPTY",
)

messages = [
    {
        "role": "user",
        "content": "Explain how useful you are.",
    }
]

response = client.chat.completions.create(
    model="EXAONE-4.5-33B",
    messages=messages,
    max_tokens=32768,
    temperature=1.0,
    top_p=0.95,
    extra_body={
        "chat_template_kwargs": {
            "enable_thinking": True,  # default: True
        }
    }, 
)
print(response)

# If needed:
# pip install langchain langchain-openai langchain-mcp-adapters
# curl -LsSf https://astral.sh/uv/install.sh | sh
# sudo apt-get update && sudo apt-get install -y nodejs npm

import os
import asyncio
from langchain_openai import ChatOpenAI
from langchain.agents import create_agent
from langchain_mcp_adapters.client import MultiServerMCPClient

def print_message(msg):
    parts = msg.content if isinstance(msg.content, list) else [{"type": "text", "text": msg.content or ""}]
    text_out, reasoning_out = [], []

    for p in parts:
        if isinstance(p, dict):
            if p.get("type") in ("text", "output_text") and p.get("text"):
                text_out.append(p["text"])
            elif p.get("type") in ("reasoning", "reasoning_text") and p.get("text"):
                reasoning_out.append(p["text"])

    if reasoning_out:
        print("\n[assistant_reasoning_content]")
        print("\n".join(reasoning_out))
    if text_out:
        print("\n[assistant_content]")
        print("\n".join(text_out))

async def main():
    model = ChatOpenAI(
        model="EXAONE-4.5-33B",
        base_url="http://localhost:8000/v1",
        api_key="EMPTY",
        temperature=1.0,
        model_kwargs={"top_p": 0.95},
    )

    client = MultiServerMCPClient({
        "filesystem": {
            "transport": "stdio",
            "command": "npx",
            "args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"],
        },
        "fetch": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["mcp-server-fetch"],
        },
        "duckduckgo": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["duckduckgo-mcp-server"],
        },
    })

    agent = create_agent(model, await client.get_tools())

    inputs = {
        "messages": [{
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": (
                        "Look at the image and identify the landmark. "
                        "Use the DuckDuckGo MCP tool to verify its name, height, and location. "
                        "Then use the fetch tool to read a fuller article page about it. "
                        "Create /tmp/mcp-demo and write a short markdown file to "
                        "/tmp/mcp-demo/landmark.md with: name, location, height, and a one-sentence summary of the article. "
                        "Finally, return only the exact file content."
                    ),
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://upload.wikimedia.org/wikipedia/commons/a/a8/Tour_Eiffel_Wikimedia_Commons.jpg"
                    },
                },
            ],
        }]
    }

    async for step in agent.astream(inputs, stream_mode="values"):
        msg = step["messages"][-1]
        if getattr(msg, "type", "") == "ai":
            print_message(msg)
            for tc in getattr(msg, "tool_calls", []) or []:
                print(f"\n[tool call] {tc['name']}({tc['args']})")

if __name__ == "__main__":
    asyncio.run(main())

@article{exaone-4.5,
  title={EXAONE 4.5 Technical Report},
  author={{LG AI Research}},
  journal={arXiv preprint arXiv:2604.08644},
  year={2026}
}