EXAONE 4.5 33B is LG Research's language model. A 33B-parameter LLM from LG AI Research in the EXAONE 4.5 generation, targeting strong multilingual and reasoning performance.
Specifications
Canonical IDlgresearch-exaone-4-5-33b
TypeLanguage
StatusActive
CreatorLG ResearchLG Research
Input ModalitiesText
Output ModalitiesText
Parameters33B
Benchmarks
Intelligence Index
#239
Coding Index
#138
GPQA
#158
HLE
#179
IFBench
#128
Time to First Token
#178
SciCode
#343
LCR
#218
TerminalBench Hard
#154
TAU2
#129
Output TPS
#410

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 4.5 33B, ranked by cheapest on-demand price. The model needs about 79 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 4.5 33B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
EXAONE 4.5 33BCurrent
EXAONE 4.0 32B ReasoningAvailable
EXAONE 4.0 32BAvailable
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-4-5-33b
exaone-4-5-33b-non-reasoning
lgresearch-exaone-4-5-33b