EXAONE 4.0

EXAONE 4.0#

EXAONE 4.0 is LG AI Research’s bilingual (English / Korean) series of auto-regressive dense transformers that unify a non-reasoning mode for general instruction following with a reasoning mode for harder problems, plus native support for tool calling and agentic use.

Furiosa-LLM runs EXAONE 4.0 in FP8 (static FP8 weights with dynamic FP8 activation quantization; the KV cache stays in 16-bit precision). FuriosaAI publishes pre-compiled FP8 builds under the furiosa-ai organization on the Hugging Face Hub, each shipping a Furiosa Executable Bundle (FXB) for running it 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.

Variants#

Model

Quantization

RNGD cards

Notes

furiosa-ai/EXAONE-4.0-32B-FP8

FP8

4

32B dense; reasoning / non-reasoning

  • Architecture: EXAONE 4.0 (dense), Exaone4ForCausalLM

  • Input / Output: Text / Text

  • Quantization: Weights are quantized to FP8 (static), following the upstream FP8 release, and activations use dynamic FP8 quantization at runtime (per-token / per-block). 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#

The simplest way to serve the model is:

# Launch the server, listening on port 8000 by default
furiosa-llm serve furiosa-ai/EXAONE-4.0-32B-FP8

To parse the model’s reasoning into a separate field, start the server with the exaone4 reasoning parser (see Reasoning below):

furiosa-llm serve furiosa-ai/EXAONE-4.0-32B-FP8 \
  --reasoning-parser exaone4

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)

Launch the server with tool calling#

To enable tool (function) calling, start the server with the hermes tool-call parser (the parser used for the EXAONE-4.0 format):

furiosa-llm serve furiosa-ai/EXAONE-4.0-32B-FP8 \
  --reasoning-parser exaone4 \
  --enable-auto-tool-choice \
  --tool-call-parser hermes

Query the server#

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

curl http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
    "model": "furiosa-ai/EXAONE-4.0-32B-FP8",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
    }' \
    | python -m json.tool

Reasoning#

When launched with --reasoning-parser exaone4, the model 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-4.0-32B-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 it is the convention OpenAI recommends for returning the chain-of-thought (CoT) in Chat Completions-compatible APIs. The OpenAI Agents SDK uses reasoning as its primary property for the CoT, and many LLM serving frameworks (such as vLLM) follow the same convention. It appears only in responses that contain reasoning content; accessing it on a response without reasoning content raises an AttributeError.

Tool calling#

With the server launched using --enable-auto-tool-choice --tool-call-parser hermes, you can pass tools 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#