LG AI Research · First MLX build 3 Jan 2026
K-EXAONE-236B-A23B
MLX
Text k-exaone
A 237B parameter text generation model from LG AI Research, with 3 MLX builds, from 5-bit to 8-bit.
- Parameters
- 237B From Hugging Face
- Quantisation
- 6-bit K-EXAONE-236B-A23B-6bit
- Memory needed
- 217 GB Estimate, unified memory
- Download
- 192 GB Weights, estimated
- Downloads
- 76 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 217 GB at 6-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/K-EXAONE-236B-A23B-6bit --prompt "Hello"MLX builds
3 on mlx-community| K-EXAONE-236B-A23B-5bit | 5-bit | 163 GB | 184 GB | 30 |
|---|---|---|---|---|
| K-EXAONE-236B-A23B-6bit | 6-bit | 192 GB | 217 GB | 76 |
| K-EXAONE-236B-A23B-8bit | 8-bit | 251 GB | 283 GB | 30 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.