8-bit Open on Hugging Face
Parameters
237B
Weights (est.)
≈ 251 GB
Mac memory (est.)
512 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/K-EXAONE-236B-A23B-8bit --prompt "Hello"
Details
- Base model
- LGAI-EXAONE/K-EXAONE-236B-A23B (quantized)
- Vendor
- LGAI-EXAONE
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- k-exaone
- Downloads
- 30 in the last 30 days · 513 all time · 0 likes
- Published
- 2026-01-04 · updated 2026-01-06 (10mo ago)
- Languages
- en, ko, es, de, ja, vi
- Tags
- exaone_moe, lg-ai, exaone, k-exaone
Other MLX builds of LGAI-EXAONE/K-EXAONE-236B-A23B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| K-EXAONE-236B-A23B-5bit | 5-bit | ≈ 163 GB | 192 GB+ | 30 |
| K-EXAONE-236B-A23B-6bit | 6-bit | ≈ 192 GB | 256 GB+ | 76 |
| K-EXAONE-236B-A23B-8bit (this one) | 8-bit | ≈ 251 GB | 512 GB+ | 30 |