All tasks / Models

K-EXAONE 2.0 (750B-A37B)

LG AI Research's open-weights K-EXAONE MoE (Apache-2.0) with 750B total and 37B active parameters.

LG AI Research
Open weights
Released 29 Jul 2026

Where it ranks

C
Chat & assistants
Models · Local · 20 on Artificial Analysis Intelligence Index (secondary benchmark)
C
Coding
Models · Local · 20 on Artificial Analysis Intelligence Index (secondary benchmark)

Facts

Vendor: LG AI Research
Family: EXAONE
Released: 29 Jul 2026
Weights: Open: download and run it yourself
License: Apache-2.0
Parameters: 749B (37B active)
GPU memory to run locally: ~428 GB (4-bit ≈ 749 B × 0.57 GB + 1.5 GB ≈ 428 GB, estimate.)
Access: Free (open weights)
Last verified: 19 Oct 2026

Price from huggingface.co, 19 Oct 2026.

Benchmark results

Benchmark	Result	Entry on the leaderboard	As of	Source
Artificial Analysis Intelligence Index	20	`K-EXAONE 2.0 0803` Raw value from the page's embedded model data; the site displays it rounded to an integer. Flagged 'estimated' by Artificial Analysis.	19 Oct 2026	artificialanalysis.ai

Where you can use it

No tracked tool lists this model yet; as open weights it runs in local runtimes.

Earlier versions

K-EXAONE 236B-A23B · Dec 2025

Sources