EXAONE 4.5

EXAONE 4.5#

EXAONE 4.5 is LG AI Research’s open-weight vision-language model. It integrates a dedicated vision encoder with the dense EXAONE 4 language-model architecture to handle images and text, and supports hybrid reasoning and tool calling.

Furiosa-LLM runs EXAONE 4.5 using the upstream FP8 release. Selected linear weights use static FP8 quantization with dynamic per-token FP8 activation quantization, while the vision encoder and attention projections stay in higher precision. FuriosaAI publishes a pre-compiled build under the furiosa-ai organization on the Hugging Face Hub, shipping a Furiosa Executable Bundle (FXB) for running the model on FuriosaAI RNGD with Furiosa-LLM. The same upstream weights also run on other frameworks (such as vLLM, SGLang, and Transformers); for usage with those, see the upstream model card linked below.

Available Models#

Model

Quantization

RNGD cards

Notes

furiosa-ai/EXAONE-4.5-33B-FP8

FP8

4

33B dense vision-language model; thinking by default

  • Architecture: EXAONE 4.5 (dense vision-language), Exaone4_5_ForConditionalGeneration

  • Input / Output: Image + Text / Text

  • Quantization: Selected linear weights are quantized to FP8 (static, per-channel), following the upstream FP8 release, and their activations use dynamic per-token FP8 quantization at runtime. The upstream configuration excludes the vision encoder, attention projections, LM head, and MTP attention projections from FP8 quantization; the KV cache stays in 16-bit precision.

Usage#

To run this model with Furiosa-LLM, follow the example commands below after installing Furiosa-LLM and its prerequisites.

Launch the server#

EXAONE 4.5 reasons by default and can switch thinking on and off (see Advanced Usage). Launch the server with the qwen3 reasoning parser so its chain of thought is separated from the final answer:

# Launch the server, listening on port 8000 by default
furiosa-llm serve furiosa-ai/EXAONE-4.5-33B-FP8 \
  --reasoning-parser qwen3

To also enable tool (function) calling, add the hermes tool-call parser; keep --reasoning-parser qwen3 so thinking is still parsed into its own field:

furiosa-llm serve furiosa-ai/EXAONE-4.5-33B-FP8 \
  --reasoning-parser qwen3 \
  --enable-auto-tool-choice \
  --tool-call-parser hermes

When the server is ready, you will see:

INFO:     Started server process [27507]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

Basic Usage#

The server exposes an OpenAI-compatible API. You can send a text-only request with curl:

curl http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
    "model": "furiosa-ai/EXAONE-4.5-33B-FP8",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
    }' \
    | python -m json.tool

To ask about an image, pass an image_url content part in the message:

curl http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
    "model": "furiosa-ai/EXAONE-4.5-33B-FP8",
    "messages": [{
        "role": "user",
        "content": [
            {"type": "image_url", "image_url": {"url": "https://github.com/LG-AI-EXAONE/EXAONE-4.5/blob/main/assets/exaone45_input1.jpg?raw=true"}},
            {"type": "text", "text": "What dish is the person preparing?"}
        ]
    }]
    }' \
    | python -m json.tool

The image_url.url field accepts a remote http:///https:// URL, an inline base64 data: URL, or a local file:// path (the last requires the --allowed-local-media-path flag described under Advanced Usage).

With --reasoning-parser qwen3, EXAONE 4.5 returns its reasoning separately from the final answer:

  • response.choices[].message.reasoning (non-streaming)

  • response.choices[].delta.reasoning (streaming)

from openai import OpenAI

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

response = client.chat.completions.create(
    model="furiosa-ai/EXAONE-4.5-33B-FP8",
    messages=[{"role": "user", "content": "How many r's are in 'strawberry'?"}],
)

print("Reasoning:", response.choices[0].message.reasoning)
print("Answer:", response.choices[0].message.content)

Note: The reasoning field is not part of the OpenAI API specification but is a widely followed convention (the OpenAI Agents SDK, vLLM, and others). It appears only in responses that contain reasoning content; accessing it otherwise raises an AttributeError.

Advanced Usage#

Multimodal serving options. This example allows local images under /srv/media, restricts remote image fetches to cdn.example.com, and limits each request to four images:

furiosa-llm serve furiosa-ai/EXAONE-4.5-33B-FP8 \
  --reasoning-parser qwen3 \
  --allowed-local-media-path /srv/media \
  --allowed-media-domains cdn.example.com \
  --image-limit-per-prompt 4

See Server Options in the Vision-Language Models guide for the full option reference and defaults.

Image processing options. This example sets a 10-second HTTP image-fetch timeout and uses min_pixels and max_pixels to bound image resizing:

furiosa-llm serve furiosa-ai/EXAONE-4.5-33B-FP8 \
  --reasoning-parser qwen3 \
  --media-io-kwargs '{"image": {"timeout": 10}}' \
  --mm-processor-kwargs '{"min_pixels": 4096, "max_pixels": 200704}'

For supported values, sizing behavior, and per-request overrides, see Multimodal Options in the Vision-Language Models guide.

Turning thinking off. EXAONE 4.5 reasons by default. To turn thinking off for a single request, pass enable_thinking through chat_template_kwargs; the response then carries no reasoning content, so read only message.content:

# Disable thinking for a single request
response = client.chat.completions.create(
    model="furiosa-ai/EXAONE-4.5-33B-FP8",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
print(response.choices[0].message.content)

To default every request to non-thinking, launch the server with --default-chat-template-kwargs (a request can still re-enable thinking with its own chat_template_kwargs):

furiosa-llm serve furiosa-ai/EXAONE-4.5-33B-FP8 \
  --reasoning-parser qwen3 \
  --default-chat-template-kwargs '{"enable_thinking": false}'

Tool calling. With the server launched using --enable-auto-tool-choice --tool-call-parser hermes (see Launch the server), pass tools in the request and let the model decide when to call them. See the Tool Calling guide for a complete client example and details on tool-choice options.

Learn more#