EXAONE 4.0 32B is LG Research's language model. A large 32B-parameter LLM from LG AI Research's EXAONE 4 series, delivering strong multilingual performance across a wide range of language understanding and generation tasks.
Specifications
Canonical IDlgresearch-exaone-4-32b
TypeLanguage
StatusActive
CreatorLG ResearchLG Research
Input ModalitiesText
Output ModalitiesText
Parameters32B
Benchmarks
Intelligence Index
#364
Math Index
#86
MMLU-Pro
#91
GPQA
#229
HLE
#201
LiveCodeBench
#54
AIME
#21
IFBench
#304
Time to First Token
#176
SciCode
#265
MATH-500
#25
AIME 2025
#86
LCR
#368
TerminalBench Hard
#302
TAU2
#352
Output TPS
#408

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Cheapest Instances to Run It

Cloud GPU instances that can host EXAONE 4.0 32B, ranked by cheapest on-demand price. The model needs about 77 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP20sAzure2× AMD Alveo U250 FPGA (64GB)128 GB$3.30/hr
g7e.2xlargeAWSRTX PRO Server 600096 GB$3.36/hr
Standard_NC24ads_A100_v4AzureNVIDIA A10080 GB$3.67/hr
7 more instances can run EXAONE 4.0 32B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
EXAONE 4.0 32BCurrent
EXAONE 4.5 33BAvailable
EXAONE 4.0 32B ReasoningAvailable
EXAONE 4.1 2BAvailable
EXAONE 4.1 2B ReasoningAvailable
EXAONE 2Available
EXAONE 2 750B A37B262K$0.600$2.40Deprecated
K-EXAONE Non-ReasoningAvailable
K-EXAONEAvailable
EXAONEAvailable

Model IDs

exaone-4-0-32b
exaone-4-0-32b-reasoning
lgresearch-exaone-4-32b