K-EXAONE 2.0

LG AI Research · lgai-exaone/k-exaone-2-0-750b-a37b

ProviderLG AI Research
Familyk-exaone
Typellm-chat
Statusactive
Released2026-07-29
Updated2026-08-07
Parameters749.4B
Open weightsyes

What it fits on

Ordered by predicted speed. Bandwidth sets decode rate; memory decides whether it runs at all.

Every figure here is computed, not measured. Fit is weights at each quantisation against device memory, with a 25% allowance for the KV cache, activations and the OS. Decode rate is the memory-bandwidth roofline at 70% efficiency. Nobody has run this model on these devices. This is a mixture-of-experts model and no card carries active-parameter counts, so these predictions use total parameters and understate the real speed.
DeviceMemoryBandwidthBest qualityWeightstok/sFastest
Apple M3 Ultra512.0 GB819.0 GB/sq4374.68 GB~1.5~1.5 q4

Where it runs

Taken from the card's availability section.

PlatformId on that platform
Hugging FaceLGAI-EXAONE/K-EXAONE-2.0-750B-A37B

Verified benchmark evidence

Each row was checked against its source by a reviewer, and carries the model identifier as actually evaluated — which is not always the same as this card's.
BenchmarkEvaluated asScoreEvidence dateSource kind
aa_lcrK-EXAONE 2.060.0%2026-09-10 evaluatedindependent evaluatorsource
critptK-EXAONE 2.00.86%2026-09-10 evaluatedindependent evaluatorsource
gdpval_aaK-EXAONE 2.020.9%2026-09-10 evaluatedindependent evaluatorsource
gpqa_diamondK-EXAONE 2.082.93%2026-09-10 evaluatedindependent evaluatorsource
scicodeK-EXAONE 2.042.01%2026-09-10 evaluatedindependent evaluatorsource

Reported benchmark scores

This card reports no benchmark scores yet.

BenchmarkCatalogue standingScore

Data

This card as JSON · See it in the graph · Edit on GitHub