OpenModelsHQ

K-EXAONE-236B-A23B

LG AI Research (EXAONE)LLMMoECustom license

K-EXAONE-236B-A23B is an open-weight language model from LG AI Research (EXAONE) with 237B parameters (mixture of experts). At 4-bit it needs about 156.9 GB of memory, so the smallest current device that fits it is the Mac Studio M5 Ultra (256GB).

Overview

Estimated memory at 4-bit
156.9GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
237B
Mixture of experts, all weights counted
Context window
256K
262,144 tokens
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
LG AI Research (EXAONE)
Released
26 Dec 2025
Parameters
237B · MoE
Type
Language
Context
262,144 tokens
HF downloads, 30 days
9,067
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
K-EXAONE-236B-A23B needs about 156.9 GB at 4-bit, 276.9 GB at 8-bit and 522.1 GB at 16-bit. At 4-bit it fits Mac Studio M5 Ultra (256GB). Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q4156.9 GB
Q8276.9 GB
BF16522.1 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 156.9 GBToo big 436%Mac Studio M5 Ultra (256GB)256 GB memory
8-bit (Q8)≈ 276.9 GBToo big 769%Mac Studio M3 Ultra (512GB)Discontinued512 GB memory
16-bit (BF16)≈ 522.1 GBToo big 1450%No single device in our directory has enough memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

Start with the MLX files, built for Apple Silicon.

mlx-community/K-EXAONE-236B-A23B-6bitCheck your Mac

With GGUF

No trusted GGUF build found yet.

Find compatible hardware

Through an API

No hosted API found.

MLX on Apple SiliconView repository
mlx_lm.generate --model mlx-community/K-EXAONE-236B-A23B-6bit \
  --prompt "Explain how a transformer works."

Example commands built from the repository ids above. They need a working install of MLX. We have not run them; check each repository for available files.

More about this model

Frequently asked questions

How much memory does K-EXAONE-236B-A23B need? At an 8k context, about 156.9 GB at 4-bit, 276.9 GB at 8-bit and 522.1 GB at 16-bit (BF16). A longer context needs more.

Can I run K-EXAONE-236B-A23B on a Mac? The smallest current Mac that fits the 4-bit estimate of 156.9 GB is the Mac Studio M5 Ultra (256GB). An MLX build is available: mlx-community/K-EXAONE-236B-A23B-6bit.

Does the full context fit? K-EXAONE-236B-A23B supports up to 262,144 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? We did not find a hosted API for this model.

License in plain English

Custom license. This model uses a custom license rather than a standard one. Read it on the model card before using the model commercially. This summary is not legal advice.

Read the license on the model card

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card, MLX repository.